Upload 29 files

Dockerfile

@@ -0,0 +1,29 @@
+# syntax=docker/dockerfile:1
+
+FROM python:3.10-bullseye
+
+EXPOSE 7865
+
+WORKDIR /app
+
+COPY . .
+
+RUN apt update && apt install -y -qq ffmpeg aria2 && apt clean
+
+RUN pip3 install --no-cache-dir -r requirements.txt
+
+RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/D40k.pth -d assets/pretrained_v2/ -o D40k.pth
+RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/G40k.pth -d assets/pretrained_v2/ -o G40k.pth
+RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0D40k.pth -d assets/pretrained_v2/ -o f0D40k.pth
+RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0G40k.pth -d assets/pretrained_v2/ -o f0G40k.pth
+
+RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP2-人声vocals+非人声instrumentals.pth -d assets/uvr5_weights/ -o HP2-人声vocals+非人声instrumentals.pth
+RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP5-主旋律人声vocals+其他instrumentals.pth -d assets/uvr5_weights/ -o HP5-主旋律人声vocals+其他instrumentals.pth
+
+RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/hubert_base.pt -d assets/hubert -o hubert_base.pt
+
+RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/rmvpe.pt -d assets/hubert -o rmvpe.pt
+
+VOLUME [ "/app/weights", "/app/opt" ]
+
+CMD ["python3", "infer-web.py"]

GUI.py

@@ -0,0 +1,1410 @@
+import os, sys
+import datetime, subprocess
+from mega import Mega
+now_dir = os.getcwd()
+sys.path.append(now_dir)
+import logging
+import shutil
+import threading
+import traceback
+import warnings
+from random import shuffle
+from subprocess import Popen
+from time import sleep
+import json
+import pathlib
+
+import fairseq
+import faiss
+import gradio as gr
+import numpy as np
+import torch
+from dotenv import load_dotenv
+from sklearn.cluster import MiniBatchKMeans
+
+from configs.config import Config
+from i18n.i18n import I18nAuto
+from infer.lib.train.process_ckpt import (
+    change_info,
+    extract_small_model,
+    merge,
+    show_info,
+)
+from infer.modules.uvr5.modules import uvr
+from infer.modules.vc.modules import VC
+logging.getLogger("numba").setLevel(logging.WARNING)
+
+logger = logging.getLogger(__name__)
+
+tmp = os.path.join(now_dir, "TEMP")
+shutil.rmtree(tmp, ignore_errors=True)
+shutil.rmtree("%s/runtime/Lib/site-packages/infer_pack" % (now_dir), ignore_errors=True)
+shutil.rmtree("%s/runtime/Lib/site-packages/uvr5_pack" % (now_dir), ignore_errors=True)
+os.makedirs(tmp, exist_ok=True)
+os.makedirs(os.path.join(now_dir, "logs"), exist_ok=True)
+os.makedirs(os.path.join(now_dir, "assets/weights"), exist_ok=True)
+os.environ["TEMP"] = tmp
+warnings.filterwarnings("ignore")
+torch.manual_seed(114514)
+
+
+load_dotenv()
+config = Config()
+vc = VC(config)
+
+if config.dml == True:
+
+    def forward_dml(ctx, x, scale):
+        ctx.scale = scale
+        res = x.clone().detach()
+        return res
+
+    fairseq.modules.grad_multiply.GradMultiply.forward = forward_dml
+i18n = I18nAuto()
+logger.info(i18n)
+# 判断是否有能用来训练和加速推理的N卡
+ngpu = torch.cuda.device_count()
+gpu_infos = []
+mem = []
+if_gpu_ok = False
+
+if torch.cuda.is_available() or ngpu != 0:
+    for i in range(ngpu):
+        gpu_name = torch.cuda.get_device_name(i)
+        if any(
+            value in gpu_name.upper()
+            for value in [
+                "10",
+                "16",
+                "20",
+                "30",
+                "40",
+                "A2",
+                "A3",
+                "A4",
+                "P4",
+                "A50",
+                "500",
+                "A60",
+                "70",
+                "80",
+                "90",
+                "M4",
+                "T4",
+                "TITAN",
+            ]
+        ):
+            # A10#A100#V100#A40#P40#M40#K80#A4500
+            if_gpu_ok = True  # 至少有一张能用的N卡
+            gpu_infos.append("%s\t%s" % (i, gpu_name))
+            mem.append(
+                int(
+                    torch.cuda.get_device_properties(i).total_memory
+                    / 1024
+                    / 1024
+                    / 1024
+                    + 0.4
+                )
+            )
+if if_gpu_ok and len(gpu_infos) > 0:
+    gpu_info = "\n".join(gpu_infos)
+    default_batch_size = min(mem) // 2
+else:
+    gpu_info = i18n("很遗憾您这没有能用的显卡来支持您训练")
+    default_batch_size = 1
+gpus = "-".join([i[0] for i in gpu_infos])
+
+
+class ToolButton(gr.Button, gr.components.FormComponent):
+    """Small button with single emoji as text, fits inside gradio forms"""
+
+    def __init__(self, **kwargs):
+        super().__init__(variant="tool", **kwargs)
+
+    def get_block_name(self):
+        return "button"
+
+
+weight_root = os.getenv("weight_root")
+weight_uvr5_root = os.getenv("weight_uvr5_root")
+index_root = os.getenv("index_root")
+
+names = []
+for name in os.listdir(weight_root):
+    if name.endswith(".pth"):
+        names.append(name)
+index_paths = []
+for root, dirs, files in os.walk(index_root, topdown=False):
+    for name in files:
+        if name.endswith(".index") and "trained" not in name:
+            index_paths.append("%s/%s" % (root, name))
+uvr5_names = []
+for name in os.listdir(weight_uvr5_root):
+    if name.endswith(".pth") or "onnx" in name:
+        uvr5_names.append(name.replace(".pth", ""))
+
+
+def change_choices():
+    names = []
+    for name in os.listdir(weight_root):
+        if name.endswith(".pth"):
+            names.append(name)
+    index_paths = []
+    for root, dirs, files in os.walk(index_root, topdown=False):
+        for name in files:
+            if name.endswith(".index") and "trained" not in name:
+                index_paths.append("%s/%s" % (root, name))
+    audio_files=[]
+    for filename in os.listdir("./audios"):
+        if filename.endswith(('.wav','.mp3','.ogg')):
+            audio_files.append('./audios/'+filename)
+    return {"choices": sorted(names), "__type__": "update"}, {
+        "choices": sorted(index_paths),
+        "__type__": "update",
+    }, {"choices": sorted(audio_files), "__type__": "update"}
+
+def clean():
+    return {"value": "", "__type__": "update"}
+
+
+def export_onnx():
+    from infer.modules.onnx.export import export_onnx as eo
+
+    eo()
+
+
+sr_dict = {
+    "32k": 32000,
+    "40k": 40000,
+    "48k": 48000,
+}
+
+
+def if_done(done, p):
+    while 1:
+        if p.poll() is None:
+            sleep(0.5)
+        else:
+            break
+    done[0] = True
+
+
+def if_done_multi(done, ps):
+    while 1:
+        # poll==None代表进程未结束
+        # 只要有一个进程未结束都不停
+        flag = 1
+        for p in ps:
+            if p.poll() is None:
+                flag = 0
+                sleep(0.5)
+                break
+        if flag == 1:
+            break
+    done[0] = True
+
+
+def preprocess_dataset(trainset_dir, exp_dir, sr, n_p):
+    sr = sr_dict[sr]
+    os.makedirs("%s/logs/%s" % (now_dir, exp_dir), exist_ok=True)
+    f = open("%s/logs/%s/preprocess.log" % (now_dir, exp_dir), "w")
+    f.close()
+    per = 3.0 if config.is_half else 3.7
+    cmd = '"%s" infer/modules/train/preprocess.py "%s" %s %s "%s/logs/%s" %s %.1f' % (
+        config.python_cmd,
+        trainset_dir,
+        sr,
+        n_p,
+        now_dir,
+        exp_dir,
+        config.noparallel,
+        per,
+    )
+    logger.info(cmd)
+    p = Popen(cmd, shell=True)  # , stdin=PIPE, stdout=PIPE,stderr=PIPE,cwd=now_dir
+    ###煞笔gr, popen read都非得全跑完了再一次性读取, 不用gr就正常读一句输出一句;只能额外弄出一个文本流定时读
+    done = [False]
+    threading.Thread(
+        target=if_done,
+        args=(
+            done,
+            p,
+        ),
+    ).start()
+    while 1:
+        with open("%s/logs/%s/preprocess.log" % (now_dir, exp_dir), "r") as f:
+            yield (f.read())
+        sleep(1)
+        if done[0]:
+            break
+    with open("%s/logs/%s/preprocess.log" % (now_dir, exp_dir), "r") as f:
+        log = f.read()
+    logger.info(log)
+    yield log
+
+
+# but2.click(extract_f0,[gpus6,np7,f0method8,if_f0_3,trainset_dir4],[info2])
+def extract_f0_feature(gpus, n_p, f0method, if_f0, exp_dir, version19, gpus_rmvpe):
+    gpus = gpus.split("-")
+    os.makedirs("%s/logs/%s" % (now_dir, exp_dir), exist_ok=True)
+    f = open("%s/logs/%s/extract_f0_feature.log" % (now_dir, exp_dir), "w")
+    f.close()
+    if if_f0:
+        if f0method != "rmvpe_gpu":
+            cmd = (
+                '"%s" infer/modules/train/extract/extract_f0_print.py "%s/logs/%s" %s %s'
+                % (
+                    config.python_cmd,
+                    now_dir,
+                    exp_dir,
+                    n_p,
+                    f0method,
+                )
+            )
+            logger.info(cmd)
+            p = Popen(
+                cmd, shell=True, cwd=now_dir
+            )  # , stdin=PIPE, stdout=PIPE,stderr=PIPE
+            ###煞笔gr, popen read都非得全跑完了再一次性读取, 不用gr就正常读一句输出一句;只能额外弄出一个文本流定时读
+            done = [False]
+            threading.Thread(
+                target=if_done,
+                args=(
+                    done,
+                    p,
+                ),
+            ).start()
+        else:
+            if gpus_rmvpe != "-":
+                gpus_rmvpe = gpus_rmvpe.split("-")
+                leng = len(gpus_rmvpe)
+                ps = []
+                for idx, n_g in enumerate(gpus_rmvpe):
+                    cmd = (
+                        '"%s" infer/modules/train/extract/extract_f0_rmvpe.py %s %s %s "%s/logs/%s" %s '
+                        % (
+                            config.python_cmd,
+                            leng,
+                            idx,
+                            n_g,
+                            now_dir,
+                            exp_dir,
+                            config.is_half,
+                        )
+                    )
+                    logger.info(cmd)
+                    p = Popen(
+                        cmd, shell=True, cwd=now_dir
+                    )  # , shell=True, stdin=PIPE, stdout=PIPE, stderr=PIPE, cwd=now_dir
+                    ps.append(p)
+                ###煞笔gr, popen read都非得全跑完了再一次性读取, 不用gr就正常读一句输出一句;只能额外弄出一个文本流定时读
+                done = [False]
+                threading.Thread(
+                    target=if_done_multi,  #
+                    args=(
+                        done,
+                        ps,
+                    ),
+                ).start()
+            else:
+                cmd = (
+                    config.python_cmd
+                    + ' infer/modules/train/extract/extract_f0_rmvpe_dml.py "%s/logs/%s" '
+                    % (
+                        now_dir,
+                        exp_dir,
+                    )
+                )
+                logger.info(cmd)
+                p = Popen(
+                    cmd, shell=True, cwd=now_dir
+                )  # , shell=True, stdin=PIPE, stdout=PIPE, stderr=PIPE, cwd=now_dir
+                p.wait()
+                done = [True]
+        while 1:
+            with open(
+                "%s/logs/%s/extract_f0_feature.log" % (now_dir, exp_dir), "r"
+            ) as f:
+                yield (f.read())
+            sleep(1)
+            if done[0]:
+                break
+        with open("%s/logs/%s/extract_f0_feature.log" % (now_dir, exp_dir), "r") as f:
+            log = f.read()
+        logger.info(log)
+        yield log
+    ####对不同part分别开多进程
+    """
+    n_part=int(sys.argv[1])
+    i_part=int(sys.argv[2])
+    i_gpu=sys.argv[3]
+    exp_dir=sys.argv[4]
+    os.environ["CUDA_VISIBLE_DEVICES"]=str(i_gpu)
+    """
+    leng = len(gpus)
+    ps = []
+    for idx, n_g in enumerate(gpus):
+        cmd = (
+            '"%s" infer/modules/train/extract_feature_print.py %s %s %s %s "%s/logs/%s" %s'
+            % (
+                config.python_cmd,
+                config.device,
+                leng,
+                idx,
+                n_g,
+                now_dir,
+                exp_dir,
+                version19,
+            )
+        )
+        logger.info(cmd)
+        p = Popen(
+            cmd, shell=True, cwd=now_dir
+        )  # , shell=True, stdin=PIPE, stdout=PIPE, stderr=PIPE, cwd=now_dir
+        ps.append(p)
+    ###煞笔gr, popen read都非得全跑完了再一次性读取, 不用gr就正常读一句输出一句;只能额外弄出一个文本流定时读
+    done = [False]
+    threading.Thread(
+        target=if_done_multi,
+        args=(
+            done,
+            ps,
+        ),
+    ).start()
+    while 1:
+        with open("%s/logs/%s/extract_f0_feature.log" % (now_dir, exp_dir), "r") as f:
+            yield (f.read())
+        sleep(1)
+        if done[0]:
+            break
+    with open("%s/logs/%s/extract_f0_feature.log" % (now_dir, exp_dir), "r") as f:
+        log = f.read()
+    logger.info(log)
+    yield log
+
+
+def get_pretrained_models(path_str, f0_str, sr2):
+    if_pretrained_generator_exist = os.access(
+        "assets/pretrained%s/%sG%s.pth" % (path_str, f0_str, sr2), os.F_OK
+    )
+    if_pretrained_discriminator_exist = os.access(
+        "assets/pretrained%s/%sD%s.pth" % (path_str, f0_str, sr2), os.F_OK
+    )
+    if not if_pretrained_generator_exist:
+        logger.warn(
+            "assets/pretrained%s/%sG%s.pth not exist, will not use pretrained model",
+            path_str,
+            f0_str,
+            sr2,
+        )
+    if not if_pretrained_discriminator_exist:
+        logger.warn(
+            "assets/pretrained%s/%sD%s.pth not exist, will not use pretrained model",
+            path_str,
+            f0_str,
+            sr2,
+        )
+    return (
+        "assets/pretrained%s/%sG%s.pth" % (path_str, f0_str, sr2)
+        if if_pretrained_generator_exist
+        else "",
+        "assets/pretrained%s/%sD%s.pth" % (path_str, f0_str, sr2)
+        if if_pretrained_discriminator_exist
+        else "",
+    )
+
+
+def change_sr2(sr2, if_f0_3, version19):
+    path_str = "" if version19 == "v1" else "_v2"
+    f0_str = "f0" if if_f0_3 else ""
+    return get_pretrained_models(path_str, f0_str, sr2)
+
+
+def change_version19(sr2, if_f0_3, version19):
+    path_str = "" if version19 == "v1" else "_v2"
+    if sr2 == "32k" and version19 == "v1":
+        sr2 = "40k"
+    to_return_sr2 = (
+        {"choices": ["40k", "48k"], "__type__": "update", "value": sr2}
+        if version19 == "v1"
+        else {"choices": ["40k", "48k", "32k"], "__type__": "update", "value": sr2}
+    )
+    f0_str = "f0" if if_f0_3 else ""
+    return (
+        *get_pretrained_models(path_str, f0_str, sr2),
+        to_return_sr2,
+    )
+
+
+def change_f0(if_f0_3, sr2, version19):  # f0method8,pretrained_G14,pretrained_D15
+    path_str = "" if version19 == "v1" else "_v2"
+    return (
+        {"visible": if_f0_3, "__type__": "update"},
+        *get_pretrained_models(path_str, "f0", sr2),
+    )
+
+
+# but3.click(click_train,[exp_dir1,sr2,if_f0_3,save_epoch10,total_epoch11,batch_size12,if_save_latest13,pretrained_G14,pretrained_D15,gpus16])
+def click_train(
+    exp_dir1,
+    sr2,
+    if_f0_3,
+    spk_id5,
+    save_epoch10,
+    total_epoch11,
+    batch_size12,
+    if_save_latest13,
+    pretrained_G14,
+    pretrained_D15,
+    gpus16,
+    if_cache_gpu17,
+    if_save_every_weights18,
+    version19,
+):
+    # 生成filelist
+    exp_dir = "%s/logs/%s" % (now_dir, exp_dir1)
+    os.makedirs(exp_dir, exist_ok=True)
+    gt_wavs_dir = "%s/0_gt_wavs" % (exp_dir)
+    feature_dir = (
+        "%s/3_feature256" % (exp_dir)
+        if version19 == "v1"
+        else "%s/3_feature768" % (exp_dir)
+    )
+    if if_f0_3:
+        f0_dir = "%s/2a_f0" % (exp_dir)
+        f0nsf_dir = "%s/2b-f0nsf" % (exp_dir)
+        names = (
+            set([name.split(".")[0] for name in os.listdir(gt_wavs_dir)])
+            & set([name.split(".")[0] for name in os.listdir(feature_dir)])
+            & set([name.split(".")[0] for name in os.listdir(f0_dir)])
+            & set([name.split(".")[0] for name in os.listdir(f0nsf_dir)])
+        )
+    else:
+        names = set([name.split(".")[0] for name in os.listdir(gt_wavs_dir)]) & set(
+            [name.split(".")[0] for name in os.listdir(feature_dir)]
+        )
+    opt = []
+    for name in names:
+        if if_f0_3:
+            opt.append(
+                "%s/%s.wav|%s/%s.npy|%s/%s.wav.npy|%s/%s.wav.npy|%s"
+                % (
+                    gt_wavs_dir.replace("\\", "\\\\"),
+                    name,
+                    feature_dir.replace("\\", "\\\\"),
+                    name,
+                    f0_dir.replace("\\", "\\\\"),
+                    name,
+                    f0nsf_dir.replace("\\", "\\\\"),
+                    name,
+                    spk_id5,
+                )
+            )
+        else:
+            opt.append(
+                "%s/%s.wav|%s/%s.npy|%s"
+                % (
+                    gt_wavs_dir.replace("\\", "\\\\"),
+                    name,
+                    feature_dir.replace("\\", "\\\\"),
+                    name,
+                    spk_id5,
+                )
+            )
+    fea_dim = 256 if version19 == "v1" else 768
+    if if_f0_3:
+        for _ in range(2):
+            opt.append(
+                "%s/logs/mute/0_gt_wavs/mute%s.wav|%s/logs/mute/3_feature%s/mute.npy|%s/logs/mute/2a_f0/mute.wav.npy|%s/logs/mute/2b-f0nsf/mute.wav.npy|%s"
+                % (now_dir, sr2, now_dir, fea_dim, now_dir, now_dir, spk_id5)
+            )
+    else:
+        for _ in range(2):
+            opt.append(
+                "%s/logs/mute/0_gt_wavs/mute%s.wav|%s/logs/mute/3_feature%s/mute.npy|%s"
+                % (now_dir, sr2, now_dir, fea_dim, spk_id5)
+            )
+    shuffle(opt)
+    with open("%s/filelist.txt" % exp_dir, "w") as f:
+        f.write("\n".join(opt))
+    logger.debug("Write filelist done")
+    # 生成config#无需生成config
+    # cmd = python_cmd + " train_nsf_sim_cache_sid_load_pretrain.py -e mi-test -sr 40k -f0 1 -bs 4 -g 0 -te 10 -se 5 -pg pretrained/f0G40k.pth -pd pretrained/f0D40k.pth -l 1 -c 0"
+    logger.info("Use gpus: %s", str(gpus16))
+    if pretrained_G14 == "":
+        logger.info("No pretrained Generator")
+    if pretrained_D15 == "":
+        logger.info("No pretrained Discriminator")
+    if version19 == "v1" or sr2 == "40k":
+        config_path = "v1/%s.json" % sr2
+    else:
+        config_path = "v2/%s.json" % sr2
+    config_save_path = os.path.join(exp_dir, "config.json")
+    if not pathlib.Path(config_save_path).exists():
+        with open(config_save_path, "w", encoding="utf-8") as f:
+            json.dump(
+                config.json_config[config_path],
+                f,
+                ensure_ascii=False,
+                indent=4,
+                sort_keys=True,
+            )
+            f.write("\n")
+    if gpus16:
+        cmd = (
+            '"%s" infer/modules/train/train.py -e "%s" -sr %s -f0 %s -bs %s -g %s -te %s -se %s %s %s -l %s -c %s -sw %s -v %s'
+            % (
+                config.python_cmd,
+                exp_dir1,
+                sr2,
+                1 if if_f0_3 else 0,
+                batch_size12,
+                gpus16,
+                total_epoch11,
+                save_epoch10,
+                "-pg %s" % pretrained_G14 if pretrained_G14 != "" else "",
+                "-pd %s" % pretrained_D15 if pretrained_D15 != "" else "",
+                1 if if_save_latest13 == i18n("是") else 0,
+                1 if if_cache_gpu17 == i18n("是") else 0,
+                1 if if_save_every_weights18 == i18n("是") else 0,
+                version19,
+            )
+        )
+    else:
+        cmd = (
+            '"%s" infer/modules/train/train.py -e "%s" -sr %s -f0 %s -bs %s -te %s -se %s %s %s -l %s -c %s -sw %s -v %s'
+            % (
+                config.python_cmd,
+                exp_dir1,
+                sr2,
+                1 if if_f0_3 else 0,
+                batch_size12,
+                total_epoch11,
+                save_epoch10,
+                "-pg %s" % pretrained_G14 if pretrained_G14 != "" else "",
+                "-pd %s" % pretrained_D15 if pretrained_D15 != "" else "",
+                1 if if_save_latest13 == i18n("是") else 0,
+                1 if if_cache_gpu17 == i18n("是") else 0,
+                1 if if_save_every_weights18 == i18n("是") else 0,
+                version19,
+            )
+        )
+    logger.info(cmd)
+    p = Popen(cmd, shell=True, cwd=now_dir)
+    p.wait()
+    return "训练结束, 您可查看控制台训练日志或实验文件夹下的train.log"
+
+
+# but4.click(train_index, [exp_dir1], info3)
+def train_index(exp_dir1, version19):
+    # exp_dir = "%s/logs/%s" % (now_dir, exp_dir1)
+    exp_dir = "logs/%s" % (exp_dir1)
+    os.makedirs(exp_dir, exist_ok=True)
+    feature_dir = (
+        "%s/3_feature256" % (exp_dir)
+        if version19 == "v1"
+        else "%s/3_feature768" % (exp_dir)
+    )
+    if not os.path.exists(feature_dir):
+        return "请先进行特征提取!"
+    listdir_res = list(os.listdir(feature_dir))
+    if len(listdir_res) == 0:
+        return "请先进行特征提取！"
+    infos = []
+    npys = []
+    for name in sorted(listdir_res):
+        phone = np.load("%s/%s" % (feature_dir, name))
+        npys.append(phone)
+    big_npy = np.concatenate(npys, 0)
+    big_npy_idx = np.arange(big_npy.shape[0])
+    np.random.shuffle(big_npy_idx)
+    big_npy = big_npy[big_npy_idx]
+    if big_npy.shape[0] > 2e5:
+        infos.append("Trying doing kmeans %s shape to 10k centers." % big_npy.shape[0])
+        yield "\n".join(infos)
+        try:
+            big_npy = (
+                MiniBatchKMeans(
+                    n_clusters=10000,
+                    verbose=True,
+                    batch_size=256 * config.n_cpu,
+                    compute_labels=False,
+                    init="random",
+                )
+                .fit(big_npy)
+                .cluster_centers_
+            )
+        except:
+            info = traceback.format_exc()
+            logger.info(info)
+            infos.append(info)
+            yield "\n".join(infos)
+
+    np.save("%s/total_fea.npy" % exp_dir, big_npy)
+    n_ivf = min(int(16 * np.sqrt(big_npy.shape[0])), big_npy.shape[0] // 39)
+    infos.append("%s,%s" % (big_npy.shape, n_ivf))
+    yield "\n".join(infos)
+    index = faiss.index_factory(256 if version19 == "v1" else 768, "IVF%s,Flat" % n_ivf)
+    # index = faiss.index_factory(256if version19=="v1"else 768, "IVF%s,PQ128x4fs,RFlat"%n_ivf)
+    infos.append("training")
+    yield "\n".join(infos)
+    index_ivf = faiss.extract_index_ivf(index)  #
+    index_ivf.nprobe = 1
+    index.train(big_npy)
+    faiss.write_index(
+        index,
+        "%s/trained_IVF%s_Flat_nprobe_%s_%s_%s.index"
+        % (exp_dir, n_ivf, index_ivf.nprobe, exp_dir1, version19),
+    )
+
+    infos.append("adding")
+    yield "\n".join(infos)
+    batch_size_add = 8192
+    for i in range(0, big_npy.shape[0], batch_size_add):
+        index.add(big_npy[i : i + batch_size_add])
+    faiss.write_index(
+        index,
+        "%s/added_IVF%s_Flat_nprobe_%s_%s_%s.index"
+        % (exp_dir, n_ivf, index_ivf.nprobe, exp_dir1, version19),
+    )
+    infos.append(
+        "成功构建索引，added_IVF%s_Flat_nprobe_%s_%s_%s.index"
+        % (n_ivf, index_ivf.nprobe, exp_dir1, version19)
+    )
+    # faiss.write_index(index, '%s/added_IVF%s_Flat_FastScan_%s.index'%(exp_dir,n_ivf,version19))
+    # infos.append("成功构建索引，added_IVF%s_Flat_FastScan_%s.index"%(n_ivf,version19))
+    yield "\n".join(infos)
+
+
+# but5.click(train1key, [exp_dir1, sr2, if_f0_3, trainset_dir4, spk_id5, gpus6, np7, f0method8, save_epoch10, total_epoch11, batch_size12, if_save_latest13, pretrained_G14, pretrained_D15, gpus16, if_cache_gpu17], info3)
+def train1key(
+    exp_dir1,
+    sr2,
+    if_f0_3,
+    trainset_dir4,
+    spk_id5,
+    np7,
+    f0method8,
+    save_epoch10,
+    total_epoch11,
+    batch_size12,
+    if_save_latest13,
+    pretrained_G14,
+    pretrained_D15,
+    gpus16,
+    if_cache_gpu17,
+    if_save_every_weights18,
+    version19,
+    gpus_rmvpe,
+):
+    infos = []
+
+    def get_info_str(strr):
+        infos.append(strr)
+        return "\n".join(infos)
+
+    ####### step1:处理数据
+    yield get_info_str(i18n("step1:正在处理数据"))
+    [get_info_str(_) for _ in preprocess_dataset(trainset_dir4, exp_dir1, sr2, np7)]
+
+    ####### step2a:提取音高
+    yield get_info_str(i18n("step2:正在提取音高&正在提取特征"))
+    [
+        get_info_str(_)
+        for _ in extract_f0_feature(
+            gpus16, np7, f0method8, if_f0_3, exp_dir1, version19, gpus_rmvpe
+        )
+    ]
+
+    ####### step3a:训练模型
+    yield get_info_str(i18n("step3a:正在训练模型"))
+    click_train(
+        exp_dir1,
+        sr2,
+        if_f0_3,
+        spk_id5,
+        save_epoch10,
+        total_epoch11,
+        batch_size12,
+        if_save_latest13,
+        pretrained_G14,
+        pretrained_D15,
+        gpus16,
+        if_cache_gpu17,
+        if_save_every_weights18,
+        version19,
+    )
+    yield get_info_str(i18n("训练结束, 您可查看控制台训练日志或实验文件夹下的train.log"))
+
+    ####### step3b:训练索引
+    [get_info_str(_) for _ in train_index(exp_dir1, version19)]
+    yield get_info_str(i18n("全流程结束！"))
+
+
+#                    ckpt_path2.change(change_info_,[ckpt_path2],[sr__,if_f0__])
+def change_info_(ckpt_path):
+    if not os.path.exists(ckpt_path.replace(os.path.basename(ckpt_path), "train.log")):
+        return {"__type__": "update"}, {"__type__": "update"}, {"__type__": "update"}
+    try:
+        with open(
+            ckpt_path.replace(os.path.basename(ckpt_path), "train.log"), "r"
+        ) as f:
+            info = eval(f.read().strip("\n").split("\n")[0].split("\t")[-1])
+            sr, f0 = info["sample_rate"], info["if_f0"]
+            version = "v2" if ("version" in info and info["version"] == "v2") else "v1"
+            return sr, str(f0), version
+    except:
+        traceback.print_exc()
+        return {"__type__": "update"}, {"__type__": "update"}, {"__type__": "update"}
+
+
+F0GPUVisible = config.dml == False
+
+
+def change_f0_method(f0method8):
+    if f0method8 == "rmvpe_gpu":
+        visible = F0GPUVisible
+    else:
+        visible = False
+    return {"visible": visible, "__type__": "update"}
+
+def find_model():
+    if len(names) > 0:
+        vc.get_vc(sorted(names)[0],None,None)
+        return sorted(names)[0]
+    else:
+        try:
+            gr.Info("Do not forget to choose a model.")
+        except:
+            pass
+        return ''
+    
+def find_audios(index=False):     
+    audio_files=[]
+    if not os.path.exists('./audios'): os.mkdir("./audios")
+    for filename in os.listdir("./audios"):
+        if filename.endswith(('.wav','.mp3','.ogg')):
+            audio_files.append("./audios/"+filename)
+    if index:
+        if len(audio_files) > 0: return sorted(audio_files)[0]
+        else: return ""
+    elif len(audio_files) > 0: return sorted(audio_files)
+    else: return []
+
+def get_index():
+    if find_model() != '':
+        chosen_model=sorted(names)[0].split(".")[0]
+        logs_path="./logs/"+chosen_model
+        if os.path.exists(logs_path):
+            for file in os.listdir(logs_path):
+                if file.endswith(".index"):
+                    return os.path.join(logs_path, file)
+            return ''
+        else:
+            return ''
+        
+def get_indexes():
+    indexes_list=[]
+    for dirpath, dirnames, filenames in os.walk("./logs/"):
+        for filename in filenames:
+            if filename.endswith(".index"):
+                indexes_list.append(os.path.join(dirpath,filename))
+    if len(indexes_list) > 0:
+        return indexes_list
+    else:
+        return ''
+    
+def save_wav(file):
+    try:
+        file_path=file.name
+        shutil.move(file_path,'./audios')
+        return './audios/'+os.path.basename(file_path)
+    except AttributeError:
+        try:
+            new_name = datetime.datetime.now().strftime("%Y-%m-%d_%H-%M-%S")+'.wav'
+            new_path='./audios/'+new_name
+            shutil.move(file,new_path)
+            return new_path
+        except TypeError:
+            return None
+
+def download_from_url(url, model):
+    if url == '':
+        return "URL cannot be left empty."
+    if model =='':
+        return "You need to name your model. For example: My-Model"
+    url = url.strip()
+    zip_dirs = ["zips", "unzips"]
+    for directory in zip_dirs:
+        if os.path.exists(directory):
+            shutil.rmtree(directory)
+    os.makedirs("zips", exist_ok=True)
+    os.makedirs("unzips", exist_ok=True)
+    zipfile = model + '.zip'
+    zipfile_path = './zips/' + zipfile
+    try:
+        if "drive.google.com" in url:
+            subprocess.run(["gdown", url, "--fuzzy", "-O", zipfile_path])
+        elif "mega.nz" in url:
+            m = Mega()
+            m.download_url(url, './zips')
+        else:
+            subprocess.run(["wget", url, "-O", zipfile_path])
+        for filename in os.listdir("./zips"):
+            if filename.endswith(".zip"):
+                zipfile_path = os.path.join("./zips/",filename)
+                shutil.unpack_archive(zipfile_path, "./unzips", 'zip')
+            else:
+                return "No zipfile found."
+        for root, dirs, files in os.walk('./unzips'):
+            for file in files:
+                file_path = os.path.join(root, file)
+                if file.endswith(".index"):
+                    os.mkdir(f'./logs/{model}')
+                    shutil.copy2(file_path,f'./logs/{model}')
+                elif "G_" not in file and "D_" not in file and file.endswith(".pth"):
+                    shutil.copy(file_path,f'./assets/weights/{model}.pth')
+        shutil.rmtree("zips")
+        shutil.rmtree("unzips")
+        return "Success."
+    except:
+        return "There's been an error."
+
+def upload_to_dataset(files, dir):
+    if dir == '':
+        dir = './dataset/'+datetime.datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
+    if not os.path.exists(dir):
+        os.makedirs(dir)
+    for file in files:
+        path=file.name
+        shutil.copy2(path,dir)
+    try:
+        gr.Info(i18n("处理数据"))
+    except:
+        pass
+    return i18n("处理数据"), {"value":dir,"__type__":"update"}
+
+with gr.Blocks(title="EasyGUI v2.9",theme=gr.themes.Base()) as app:
+    gr.HTML("<h1> EasyGUI v2.9 </h1>")
+    with gr.Tabs():
+        with gr.TabItem(i18n("模型推理")):
+            with gr.Row():
+                sid0 = gr.Dropdown(label=i18n("推理音色"), choices=sorted(names), value=find_model())
+                refresh_button = gr.Button(i18n("刷新音色列表和索引路径"), variant="primary")
+                #clean_button = gr.Button(i18n("卸载音色省显存"), variant="primary")
+                spk_item = gr.Slider(
+                    minimum=0,
+                    maximum=2333,
+                    step=1,
+                    label=i18n("请选择说话人id"),
+                    value=0,
+                    visible=False,
+                    interactive=True,
+                )
+                #clean_button.click(
+                #    fn=clean, inputs=[], outputs=[sid0], api_name="infer_clean"
+                #)
+                vc_transform0 = gr.Number(
+                    label=i18n("变调(整数, 半音数量, 升八度12降八度-12)"), value=0
+                )
+                but0 = gr.Button(i18n("转换"), variant="primary")
+            with gr.Row():
+                with gr.Column():
+                    with gr.Row():
+                        dropbox = gr.File(label="Drop your audio here & hit the Reload button.")
+                    with gr.Row():
+                        record_button=gr.Audio(source="microphone", label="OR Record audio.", type="filepath")
+                    with gr.Row():
+                        input_audio0 = gr.Dropdown(
+                            label=i18n("输入待处理音频文件路径(默认是正确格式示例)"),
+                            value=find_audios(True),
+                            choices=find_audios()
+                        )
+                        record_button.change(fn=save_wav, inputs=[record_button], outputs=[input_audio0])
+                        dropbox.upload(fn=save_wav, inputs=[dropbox], outputs=[input_audio0])
+                with gr.Column():
+                    with gr.Accordion(label=i18n("自动检测index路径,下拉式选择(dropdown)"), open=False):
+                        file_index2 = gr.Dropdown(
+                            label=i18n("自动检测index路径,下拉式选择(dropdown)"),
+                            choices=get_indexes(),
+                            interactive=True,
+                            value=get_index()
+                        )
+                        index_rate1 = gr.Slider(
+                            minimum=0,
+                            maximum=1,
+                            label=i18n("检索特征占比"),
+                            value=0.66,
+                            interactive=True,
+                        )
+                    vc_output2 = gr.Audio(label=i18n("输出音频(右下角三个点,点了可以下载)"))
+                    with gr.Accordion(label=i18n("常规设置"), open=False):
+                        f0method0 = gr.Radio(
+                            label=i18n(
+                                "选择音高提取算法,输入歌声可用pm提速,harvest低音好但巨慢无比,crepe效果好但吃GPU,rmvpe效果最好且微吃GPU"
+                            ),
+                            choices=["pm", "harvest", "crepe", "rmvpe"]
+                            if config.dml == False
+                            else ["pm", "harvest", "rmvpe"],
+                            value="rmvpe",
+                            interactive=True,
+                        )
+                        filter_radius0 = gr.Slider(
+                            minimum=0,
+                            maximum=7,
+                            label=i18n(">=3则使用对harvest音高识别的结果使用中值滤波，数值为滤波半径，使用可以削弱哑音"),
+                            value=3,
+                            step=1,
+                            interactive=True,
+                        )
+                        resample_sr0 = gr.Slider(
+                            minimum=0,
+                            maximum=48000,
+                            label=i18n("后处理重采样至最终采样率，0为不进行重采样"),
+                            value=0,
+                            step=1,
+                            interactive=True,
+                        )
+                        rms_mix_rate0 = gr.Slider(
+                            minimum=0,
+                            maximum=1,
+                            label=i18n("输入源音量包络替换输出音量包络融合比例，越靠近1越使用输出包络"),
+                            value=0.21,
+                            interactive=True,
+                        )
+                        protect0 = gr.Slider(
+                            minimum=0,
+                            maximum=0.5,
+                            label=i18n(
+                                "保护清辅音和呼吸声，防止电音撕裂等artifact，拉满0.5不开启，调低加大保护力度但可能降低索引效果"
+                            ),
+                            value=0.33,
+                            step=0.01,
+                            interactive=True,
+                        )
+                    file_index1 = gr.Textbox(
+                        label=i18n("特征检索库文件路径,为空则使用下拉的选择结果"),
+                        value="",
+                        interactive=True,
+                        visible=False
+                    )
+                    refresh_button.click(
+                        fn=change_choices,
+                        inputs=[],
+                        outputs=[sid0, file_index2, input_audio0],
+                        api_name="infer_refresh",
+                    )
+                    # file_big_npy1 = gr.Textbox(
+                    #     label=i18n("特征文件路径"),
+                    #     value="E:\\codes\py39\\vits_vc_gpu_train\\logs\\mi-test-1key\\total_fea.npy",
+                    #     interactive=True,
+                    # )
+            with gr.Row():
+                f0_file = gr.File(label=i18n("F0曲线文件, 可选, 一行一个音高, 代替默认F0及升降调"), visible=False)
+            with gr.Row():
+                vc_output1 = gr.Textbox(label=i18n("输出信息"))
+                but0.click(
+                    vc.vc_single,  
+                    [
+                        spk_item,
+                        input_audio0,
+                        vc_transform0,
+                        f0_file,
+                        f0method0,
+                        file_index1,
+                        file_index2,
+                        # file_big_npy1,
+                        index_rate1,
+                        filter_radius0,
+                        resample_sr0,
+                        rms_mix_rate0,
+                        protect0,
+                    ],
+                    [vc_output1, vc_output2],
+                    api_name="infer_convert",
+                )
+            with gr.Row():
+                with gr.Accordion(open=False, label=i18n("批量转换, 输入待转换音频文件夹, 或上传多个音频文件, 在指定文件夹(默认opt)下输出转换的音频. ")):                
+                    with gr.Column():
+                        vc_transform1 = gr.Number(
+                            label=i18n("变调(整数, 半音数量, 升八度12降八度-12)"), value=0
+                        )
+                        opt_input = gr.Textbox(label=i18n("指定输出文件夹"), value="opt")
+                        f0method1 = gr.Radio(
+                            label=i18n(
+                                "选择音高提取算法,输入歌声可用pm提速,harvest低音好但巨慢无比,crepe效果好但吃GPU,rmvpe效果最好且微吃GPU"
+                            ),
+                            choices=["pm", "harvest", "crepe", "rmvpe"]
+                            if config.dml == False
+                            else ["pm", "harvest", "rmvpe"],
+                            value="pm",
+                            interactive=True,
+                        )
+                        filter_radius1 = gr.Slider(
+                            minimum=0,
+                            maximum=7,
+                            label=i18n(">=3则使用对harvest音高识别的结果使用中值滤波，数值为滤波半径，使用可以削弱哑音"),
+                            value=3,
+                            step=1,
+                            interactive=True,
+                        )
+                    with gr.Column():
+                        file_index3 = gr.Textbox(
+                            label=i18n("特征检索库文件路径,为空则使用下拉的选择结果"),
+                            value="",
+                            interactive=True,
+                            visible=False
+                        )
+                        file_index4 = gr.Dropdown(
+                            label=i18n("自动检测index路径,下拉式选择(dropdown)"),
+                            choices=sorted(index_paths),
+                            interactive=True,
+                        )
+                        refresh_button.click(
+                            fn=lambda: change_choices()[1],
+                            inputs=[],
+                            outputs=file_index4,
+                            api_name="infer_refresh_batch",
+                        )
+                        # file_big_npy2 = gr.Textbox(
+                        #     label=i18n("特征文件路径"),
+                        #     value="E:\\codes\\py39\\vits_vc_gpu_train\\logs\\mi-test-1key\\total_fea.npy",
+                        #     interactive=True,
+                        # )
+                        index_rate2 = gr.Slider(
+                            minimum=0,
+                            maximum=1,
+                            label=i18n("检索特征占比"),
+                            value=1,
+                            interactive=True,
+                        )
+                    with gr.Column():
+                        resample_sr1 = gr.Slider(
+                            minimum=0,
+                            maximum=48000,
+                            label=i18n("后处理重采样至最终采样率，0为不进行重采样"),
+                            value=0,
+                            step=1,
+                            interactive=True,
+                        )
+                        rms_mix_rate1 = gr.Slider(
+                            minimum=0,
+                            maximum=1,
+                            label=i18n("输入源音量包络替换输出音量包络融合比例，越靠近1越使用输出包络"),
+                            value=1,
+                            interactive=True,
+                        )
+                        protect1 = gr.Slider(
+                            minimum=0,
+                            maximum=0.5,
+                            label=i18n(
+                                "保护清辅音和呼吸声，防止电音撕裂等artifact，拉满0.5不开启，调低加大保护力度但可能降低索引效果"
+                            ),
+                            value=0.33,
+                            step=0.01,
+                            interactive=True,
+                        )
+                    with gr.Column():
+                        dir_input = gr.Textbox(
+                            label=i18n("输入待处理音频文件夹路径(去文件管理器地址栏拷就行了)"),
+                            value="E:\codes\py39\\test-20230416b\\todo-songs",
+                        )
+                        inputs = gr.File(
+                            file_count="multiple", label=i18n("也可批量输入音频文件, 二选一, 优先读文件夹")
+                        )
+                    with gr.Row():
+                        format1 = gr.Radio(
+                            label=i18n("导出文件格式"),
+                            choices=["wav", "flac", "mp3", "m4a"],
+                            value="flac",
+                            interactive=True,
+                        )
+                        but1 = gr.Button(i18n("转换"), variant="primary")
+                        vc_output3 = gr.Textbox(label=i18n("输出信息"))
+                        but1.click(
+                            vc.vc_multi,
+                            [
+                                spk_item,
+                                dir_input,
+                                opt_input,
+                                inputs,
+                                vc_transform1,
+                                f0method1,
+                                file_index3,
+                                file_index4,
+                                # file_big_npy2,
+                                index_rate2,
+                                filter_radius1,
+                                resample_sr1,
+                                rms_mix_rate1,
+                                protect1,
+                                format1,
+                            ],
+                            [vc_output3],
+                            api_name="infer_convert_batch",
+                        )
+            sid0.change(
+                fn=vc.get_vc,
+                inputs=[sid0, protect0, protect1],
+                outputs=[spk_item, protect0, protect1, file_index2, file_index4],
+            )
+        with gr.TabItem("Download Model"):
+            with gr.Row():
+                url=gr.Textbox(label="Enter the URL to the Model:")
+            with gr.Row():
+                model = gr.Textbox(label="Name your model:")
+                download_button=gr.Button("Download")
+            with gr.Row():
+                status_bar=gr.Textbox(label="")
+                download_button.click(fn=download_from_url, inputs=[url, model], outputs=[status_bar])
+            with gr.Row():
+                gr.Markdown(
+                """
+                ❤️ If you like the EasyGUI, help me keep it.❤️ 
+                https://paypal.me/lesantillan
+                """
+                )
+        with gr.TabItem(i18n("训练")):
+            with gr.Row():
+                with gr.Column():
+                    exp_dir1 = gr.Textbox(label=i18n("输入实验名"), value="My-Voice")
+                    np7 = gr.Slider(
+                        minimum=0,
+                        maximum=config.n_cpu,
+                        step=1,
+                        label=i18n("提取音高和处理数据使用的CPU进程数"),
+                        value=int(np.ceil(config.n_cpu / 1.5)),
+                        interactive=True,
+                    )
+                    sr2 = gr.Radio(
+                        label=i18n("目标采样率"),
+                        choices=["40k", "48k"],
+                        value="40k",
+                        interactive=True,
+                        visible=False
+                    )
+                    if_f0_3 = gr.Radio(
+                        label=i18n("模型是否带音高指导(唱歌一定要, 语音可以不要)"),
+                        choices=[True, False],
+                        value=True,
+                        interactive=True,
+                        visible=False
+                    )
+                    version19 = gr.Radio(
+                        label=i18n("版本"),
+                        choices=["v1", "v2"],
+                        value="v2",
+                        interactive=True,
+                        visible=False,
+                    )
+                    trainset_dir4 = gr.Textbox(
+                        label=i18n("输入训练文件夹路径"), value='./dataset/'+datetime.datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
+                    )
+                    easy_uploader = gr.Files(label=i18n("也可批量输入音频文件, 二选一, 优先读文件夹"),file_types=['audio'])
+                    but1 = gr.Button(label=i18n("处理数据"), variant="primary")
+                    info1 = gr.Textbox(label=i18n("输出信息"), value="")
+                    easy_uploader.upload(fn=upload_to_dataset, inputs=[easy_uploader, trainset_dir4], outputs=[info1, trainset_dir4])
+                    gpus6 = gr.Textbox(
+                        label=i18n("以-分隔输入使用的卡号, 例如   0-1-2   使用卡0和卡1和卡2"),
+                        value=gpus,
+                        interactive=True,
+                        visible=F0GPUVisible,
+                    )
+                    gpu_info9 = gr.Textbox(
+                        label=i18n("显卡信息"), value=gpu_info, visible=F0GPUVisible
+                    )
+                    spk_id5 = gr.Slider(
+                        minimum=0,
+                        maximum=4,
+                        step=1,
+                        label=i18n("请指定说话人id"),
+                        value=0,
+                        interactive=True,
+                        visible=False
+                    )
+                    but1.click(
+                        preprocess_dataset,
+                        [trainset_dir4, exp_dir1, sr2, np7],
+                        [info1],
+                        api_name="train_preprocess",
+                    ) 
+                with gr.Column():
+                    f0method8 = gr.Radio(
+                        label=i18n(
+                            "选择音高提取算法:输入歌声可用pm提速,高质量语音但CPU差可用dio提速,harvest质量更好但慢,rmvpe效果最好且微吃CPU/GPU"
+                        ),
+                        choices=["pm", "harvest", "dio", "rmvpe", "rmvpe_gpu"],
+                        value="rmvpe_gpu",
+                        interactive=True,
+                    )
+                    gpus_rmvpe = gr.Textbox(
+                        label=i18n(
+                            "rmvpe卡号配置：以-分隔输入使用的不同进程卡号,例如0-0-1使用在卡0上跑2个进程并在卡1上跑1个进程"
+                        ),
+                        value="%s-%s" % (gpus, gpus),
+                        interactive=True,
+                        visible=F0GPUVisible,
+                    )
+                    but2 = gr.Button(i18n("特征提取"), variant="primary")
+                    info2 = gr.Textbox(label=i18n("输出信息"), value="", max_lines=8)
+                    f0method8.change(
+                        fn=change_f0_method,
+                        inputs=[f0method8],
+                        outputs=[gpus_rmvpe],
+                    )
+                    but2.click(
+                        extract_f0_feature,
+                        [
+                            gpus6,
+                            np7,
+                            f0method8,
+                            if_f0_3,
+                            exp_dir1,
+                            version19,
+                            gpus_rmvpe,
+                        ],
+                        [info2],
+                        api_name="train_extract_f0_feature",
+                    )
+                with gr.Column():
+                    total_epoch11 = gr.Slider(
+                        minimum=2,
+                        maximum=1000,
+                        step=1,
+                        label=i18n("总训练轮数total_epoch"),
+                        value=150,
+                        interactive=True,
+                    )
+                    gpus16 = gr.Textbox(
+                            label=i18n("以-分隔输入使用的卡号, 例如   0-1-2   使用卡0和卡1和卡2"),
+                            value="0",
+                            interactive=True,
+                            visible=True
+                        )
+                    but3 = gr.Button(i18n("训练模型"), variant="primary")
+                    but4 = gr.Button(i18n("训练特征索引"), variant="primary")
+                    info3 = gr.Textbox(label=i18n("输出信息"), value="", max_lines=10)
+                    with gr.Accordion(label=i18n("常规设置"), open=False):
+                        save_epoch10 = gr.Slider(
+                            minimum=1,
+                            maximum=50,
+                            step=1,
+                            label=i18n("保存频率save_every_epoch"),
+                            value=25,
+                            interactive=True,
+                        )
+                        batch_size12 = gr.Slider(
+                            minimum=1,
+                            maximum=40,
+                            step=1,
+                            label=i18n("每张显卡的batch_size"),
+                            value=default_batch_size,
+                            interactive=True,
+                        )
+                        if_save_latest13 = gr.Radio(
+                            label=i18n("是否仅保存最新的ckpt文件以节省硬盘空间"),
+                            choices=[i18n("是"), i18n("否")],
+                            value=i18n("是"),
+                            interactive=True,
+                        )
+                        if_cache_gpu17 = gr.Radio(
+                            label=i18n(
+                                "是否缓存所有训练集至显存. 10min以下小数据可缓存以加速训练, 大数据缓存会炸显存也加不了多少速"
+                            ),
+                            choices=[i18n("是"), i18n("否")],
+                            value=i18n("否"),
+                            interactive=True,
+                        )
+                        if_save_every_weights18 = gr.Radio(
+                            label=i18n("是否在每次保存时间点将最终小模型保存至weights文件夹"),
+                            choices=[i18n("是"), i18n("否")],
+                            value=i18n("是"),
+                            interactive=True,
+                        )
+                    with gr.Row():
+                        pretrained_G14 = gr.Textbox(
+                            label=i18n("加载预训练底模G路径"),
+                            value="assets/pretrained_v2/f0G40k.pth",
+                            interactive=True,
+                            visible=False
+                        )
+                        pretrained_D15 = gr.Textbox(
+                            label=i18n("加载预训练底模D路径"),
+                            value="assets/pretrained_v2/f0D40k.pth",
+                            interactive=True,
+                            visible=False
+                        )
+                        sr2.change(
+                            change_sr2,
+                            [sr2, if_f0_3, version19],
+                            [pretrained_G14, pretrained_D15],
+                        )
+                        version19.change(
+                            change_version19,
+                            [sr2, if_f0_3, version19],
+                            [pretrained_G14, pretrained_D15, sr2],
+                        )
+                        if_f0_3.change(
+                            change_f0,
+                            [if_f0_3, sr2, version19],
+                            [f0method8, pretrained_G14, pretrained_D15],
+                        )
+                    with gr.Row():
+                        but5 = gr.Button(i18n("一键训练"), variant="primary", visible=False)
+                        but3.click(
+                            click_train,
+                            [
+                                exp_dir1,
+                                sr2,
+                                if_f0_3,
+                                spk_id5,
+                                save_epoch10,
+                                total_epoch11,
+                                batch_size12,
+                                if_save_latest13,
+                                pretrained_G14,
+                                pretrained_D15,
+                                gpus16,
+                                if_cache_gpu17,
+                                if_save_every_weights18,
+                                version19,
+                            ],
+                            info3,
+                            api_name="train_start",
+                        )
+                        but4.click(train_index, [exp_dir1, version19], info3)
+                        but5.click(
+                            train1key,
+                            [
+                                exp_dir1,
+                                sr2,
+                                if_f0_3,
+                                trainset_dir4,
+                                spk_id5,
+                                np7,
+                                f0method8,
+                                save_epoch10,
+                                total_epoch11,
+                                batch_size12,
+                                if_save_latest13,
+                                pretrained_G14,
+                                pretrained_D15,
+                                gpus16,
+                                if_cache_gpu17,
+                                if_save_every_weights18,
+                                version19,
+                                gpus_rmvpe,
+                            ],
+                            info3,
+                            api_name="train_start_all",
+                        )
+
+    if config.iscolab:
+        app.queue(concurrency_count=511, max_size=1022).launch(share=True)
+    else:
+        app.queue(concurrency_count=511, max_size=1022).launch(
+            server_name="0.0.0.0",
+            inbrowser=not config.noautoopen,
+            server_port=config.listen_port,
+            quiet=True,
+        )

LICENSE

@@ -0,0 +1,23 @@
+MIT License
+
+Copyright (c) 2023 liujing04
+Copyright (c) 2023 源文雨
+Copyright (c) 2023 Ftps
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

MIT协议暨相关引用库协议

@@ -0,0 +1,45 @@
+本软件及其相关代码以MIT协议开源，作者不对软件具备任何控制力，使用软件者、传播软件导出的声音者自负全责。
+如不认可该条款，则不能使用或引用软件包内任何代码和文件。
+
+特此授予任何获得本软件和相关文档文件（以下简称“软件”）副本的人免费使用、复制、修改、合并、出版、分发、再授权和/或销售本软件的权利，以及授予本软件所提供的人使用本软件的权利，但须符合以下条件：
+上述版权声明和本许可声明应包含在软件的所有副本或实质部分中。
+软件是“按原样”提供的，没有任何明示或暗示的保证，包括但不限于适销性、适用于特定目的和不侵权的保证。在任何情况下，作者或版权持有人均不承担因软件或软件的使用或其他交易而产生、产生或与之相关的任何索赔、损害赔偿或其他责任，无论是在合同诉讼、侵权诉讼还是其他诉讼中。
+
+
+The LICENCEs for related libraries are as follows.
+相关引用库协议如下：
+
+ContentVec
+https://github.com/auspicious3000/contentvec/blob/main/LICENSE
+MIT License
+
+VITS
+https://github.com/jaywalnut310/vits/blob/main/LICENSE
+MIT License
+
+HIFIGAN
+https://github.com/jik876/hifi-gan/blob/master/LICENSE
+MIT License
+
+gradio
+https://github.com/gradio-app/gradio/blob/main/LICENSE
+Apache License 2.0
+
+ffmpeg
+https://github.com/FFmpeg/FFmpeg/blob/master/COPYING.LGPLv3
+https://github.com/BtbN/FFmpeg-Builds/releases/download/autobuild-2021-02-28-12-32/ffmpeg-n4.3.2-160-gfbb9368226-win64-lgpl-4.3.zip
+LPGLv3 License
+MIT License
+
+ultimatevocalremovergui
+https://github.com/Anjok07/ultimatevocalremovergui/blob/master/LICENSE
+https://github.com/yang123qwe/vocal_separation_by_uvr5
+MIT License
+
+audio-slicer
+https://github.com/openvpi/audio-slicer/blob/main/LICENSE
+MIT License
+
+PySimpleGUI
+https://github.com/PySimpleGUI/PySimpleGUI/blob/master/license.txt
+LPGLv3 License

README.md

@@ -1,13 +1,32 @@
----
-title: Nw
-emoji: 🏢
-colorFrom: pink
-colorTo: red
-sdk: gradio
-sdk_version: 4.10.0
-app_file: app.py
-pinned: false
-license: apache-2.0
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+[![Open In Colab](https://img.shields.io/badge/Colab-F9AB00?style=for-the-badge&logo=googlecolab&color=525252)](https://colab.research.google.com/drive/1r4IRL0UA7JEoZ0ZK8PKfMyTIBHKpyhcw)
+
+# Local Installation
+If you already have RVC installed, then just download GUI.py and drop it in the root folder!
+If you need to install RVC, I recommend you check the [original repo](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI)
+Or read this at least.
+
+I recommend you use a virtual environment
+
+```bash
+python -m venv RVC
+cd RVC
+git clone https://github.com/777gt/-EVC-
+Scripts/activate.bat
+pip install torch torchvision torchaudio
+pip install -r "-EVC-/requirements.txt"
+```
+If you're on Windows, like me, and don't have an NVIDA graphics card, install the requirements from a different .txt:
+```bash
+pip install -r "-EVC-/requirements-dml.txt"
+```
+Also, do not forget to download the necessary models. EasyGUI uses RVC 2 40k models.
+
+```bash
+wget https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/rmvpe.pt -O ./assets/rmvpe/rmvpe.pt
+wget https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/rmvpe.onnx -O ./assets/rmvpe/rmvpe.onnx
+wget https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/hubert_base.pt -O ./assets/hubert/hubert_base.pt
+wget https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/D40k.pth -O ./assets/pretrained_v2/D40k.pth
+wget https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/G40k.pth -O ./assets/pretrained_v2/G40k.pth
+wget https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0D40k.pth -O ./assets/pretrained_v2/f0D40k.pth
+wget https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0G40k.pth -O ./assets/pretrained_v2/f0G40k.pth
+```

Retrieval_based_Voice_Conversion_WebUI.ipynb

@@ -0,0 +1,403 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# [Retrieval-based-Voice-Conversion-WebUI](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI) Training notebook"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "ZFFCx5J80SGa"
+   },
+   "source": [
+    "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/main/Retrieval_based_Voice_Conversion_WebUI.ipynb)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "GmFP6bN9dvOq"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 查看显卡\n",
+    "!nvidia-smi"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "jwu07JgqoFON"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 挂载谷歌云盘\n",
+    "\n",
+    "from google.colab import drive\n",
+    "\n",
+    "drive.mount(\"/content/drive\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "wjddIFr1oS3W"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 安装依赖\n",
+    "!apt-get -y install build-essential python3-dev ffmpeg\n",
+    "!pip3 install --upgrade setuptools wheel\n",
+    "!pip3 install --upgrade pip\n",
+    "!pip3 install faiss-cpu==1.7.2 fairseq gradio==3.14.0 ffmpeg ffmpeg-python praat-parselmouth pyworld numpy==1.23.5 numba==0.56.4 librosa==0.9.2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "ge_97mfpgqTm"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 克隆仓库\n",
+    "\n",
+    "!git clone --depth=1 -b stable https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI\n",
+    "%cd /content/Retrieval-based-Voice-Conversion-WebUI\n",
+    "!mkdir -p pretrained uvr5_weights"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "BLDEZADkvlw1"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 更新仓库（一般无需执行）\n",
+    "!git pull"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "pqE0PrnuRqI2"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 安装aria2\n",
+    "!apt -y install -qq aria2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "UG3XpUwEomUz"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 下载底模\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o D32k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o D40k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o D48k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/G32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o G32k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/G40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o G40k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/G48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o G48k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0D32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0D32k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0D40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0D40k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0D48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0D48k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0G32k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0G40k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0G48k.pth"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "HugjmZqZRuiF"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 下载人声分离模型\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP2-人声vocals+非人声instrumentals.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/uvr5_weights -o HP2-人声vocals+非人声instrumentals.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP5-主旋律人声vocals+其他instrumentals.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/uvr5_weights -o HP5-主旋律人声vocals+其他instrumentals.pth"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "2RCaT9FTR0ej"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 下载hubert_base\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/hubert_base.pt -d /content/Retrieval-based-Voice-Conversion-WebUI -o hubert_base.pt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# @title #下载rmvpe模型\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/rmvpe.pt -d /content/Retrieval-based-Voice-Conversion-WebUI -o rmvpe.pt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "Mwk7Q0Loqzjx"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 从谷歌云盘加载打包好的数据集到/content/dataset\n",
+    "\n",
+    "# @markdown 数据集位置\n",
+    "DATASET = (\n",
+    "    \"/content/drive/MyDrive/dataset/lulu20230327_32k.zip\"  # @param {type:\"string\"}\n",
+    ")\n",
+    "\n",
+    "!mkdir -p /content/dataset\n",
+    "!unzip -d /content/dataset -B {DATASET}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "PDlFxWHWEynD"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 重命名数据集中的重名文件\n",
+    "!ls -a /content/dataset/\n",
+    "!rename 's/(\\w+)\\.(\\w+)~(\\d*)/$1_$3.$2/' /content/dataset/*.*~*"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "7vh6vphDwO0b"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 启动web\n",
+    "%cd /content/Retrieval-based-Voice-Conversion-WebUI\n",
+    "# %load_ext tensorboard\n",
+    "# %tensorboard --logdir /content/Retrieval-based-Voice-Conversion-WebUI/logs\n",
+    "!python3 infer-web.py --colab --pycmd python3"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "FgJuNeAwx5Y_"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 手动将训练后的模型文件备份到谷歌云盘\n",
+    "# @markdown 需要自己查看logs文件夹下模型的文件名，手动修改下方命令末尾的文件名\n",
+    "\n",
+    "# @markdown 模型名\n",
+    "MODELNAME = \"lulu\"  # @param {type:\"string\"}\n",
+    "# @markdown 模型epoch\n",
+    "MODELEPOCH = 9600  # @param {type:\"integer\"}\n",
+    "\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/drive/MyDrive/{MODELNAME}_D_{MODELEPOCH}.pth\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/drive/MyDrive/{MODELNAME}_G_{MODELEPOCH}.pth\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/added_*.index /content/drive/MyDrive/\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/total_*.npy /content/drive/MyDrive/\n",
+    "\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/weights/{MODELNAME}.pth /content/drive/MyDrive/{MODELNAME}{MODELEPOCH}.pth"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "OVQoLQJXS7WX"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 从谷歌云盘恢复pth\n",
+    "# @markdown 需要自己查看logs文件夹下模型的文件名，手动修改下方命令末尾的文件名\n",
+    "\n",
+    "# @markdown 模型名\n",
+    "MODELNAME = \"lulu\"  # @param {type:\"string\"}\n",
+    "# @markdown 模型epoch\n",
+    "MODELEPOCH = 7500  # @param {type:\"integer\"}\n",
+    "\n",
+    "!mkdir -p /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}\n",
+    "\n",
+    "!cp /content/drive/MyDrive/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth\n",
+    "!cp /content/drive/MyDrive/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth\n",
+    "!cp /content/drive/MyDrive/*.index /content/\n",
+    "!cp /content/drive/MyDrive/*.npy /content/\n",
+    "!cp /content/drive/MyDrive/{MODELNAME}{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/weights/{MODELNAME}.pth"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "ZKAyuKb9J6dz"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 手动预处理（不推荐）\n",
+    "# @markdown 模型名\n",
+    "MODELNAME = \"lulu\"  # @param {type:\"string\"}\n",
+    "# @markdown 采样率\n",
+    "BITRATE = 48000  # @param {type:\"integer\"}\n",
+    "# @markdown 使用的进程数\n",
+    "THREADCOUNT = 8  # @param {type:\"integer\"}\n",
+    "\n",
+    "!python3 trainset_preprocess_pipeline_print.py /content/dataset {BITRATE} {THREADCOUNT} logs/{MODELNAME} True"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "CrxJqzAUKmPJ"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 手动提取特征（不推荐）\n",
+    "# @markdown 模型名\n",
+    "MODELNAME = \"lulu\"  # @param {type:\"string\"}\n",
+    "# @markdown 使用的进程数\n",
+    "THREADCOUNT = 8  # @param {type:\"integer\"}\n",
+    "# @markdown 音高提取算法\n",
+    "ALGO = \"harvest\"  # @param {type:\"string\"}\n",
+    "\n",
+    "!python3 extract_f0_print.py logs/{MODELNAME} {THREADCOUNT} {ALGO}\n",
+    "\n",
+    "!python3 extract_feature_print.py cpu 1 0 0 logs/{MODELNAME}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "IMLPLKOaKj58"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 手动训练（不推荐）\n",
+    "# @markdown 模型名\n",
+    "MODELNAME = \"lulu\"  # @param {type:\"string\"}\n",
+    "# @markdown 使用的GPU\n",
+    "USEGPU = \"0\"  # @param {type:\"string\"}\n",
+    "# @markdown 批大小\n",
+    "BATCHSIZE = 32  # @param {type:\"integer\"}\n",
+    "# @markdown 停止的epoch\n",
+    "MODELEPOCH = 3200  # @param {type:\"integer\"}\n",
+    "# @markdown 保存epoch间隔\n",
+    "EPOCHSAVE = 100  # @param {type:\"integer\"}\n",
+    "# @markdown 采样率\n",
+    "MODELSAMPLE = \"48k\"  # @param {type:\"string\"}\n",
+    "# @markdown 是否缓存训练集\n",
+    "CACHEDATA = 1  # @param {type:\"integer\"}\n",
+    "# @markdown 是否仅保存最新的ckpt文件\n",
+    "ONLYLATEST = 0  # @param {type:\"integer\"}\n",
+    "\n",
+    "!python3 train_nsf_sim_cache_sid_load_pretrain.py -e lulu -sr {MODELSAMPLE} -f0 1 -bs {BATCHSIZE} -g {USEGPU} -te {MODELEPOCH} -se {EPOCHSAVE} -pg pretrained/f0G{MODELSAMPLE}.pth -pd pretrained/f0D{MODELSAMPLE}.pth -l {ONLYLATEST} -c {CACHEDATA}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "haYA81hySuDl"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 删除其它pth，只留选中的（慎点，仔细看代码）\n",
+    "# @markdown 模型名\n",
+    "MODELNAME = \"lulu\"  # @param {type:\"string\"}\n",
+    "# @markdown 选中模型epoch\n",
+    "MODELEPOCH = 9600  # @param {type:\"integer\"}\n",
+    "\n",
+    "!echo \"备份选中的模型。。。\"\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/{MODELNAME}_D_{MODELEPOCH}.pth\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/{MODELNAME}_G_{MODELEPOCH}.pth\n",
+    "\n",
+    "!echo \"正在删除。。。\"\n",
+    "!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}\n",
+    "!rm /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/*.pth\n",
+    "\n",
+    "!echo \"恢复选中的模型。。。\"\n",
+    "!mv /content/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth\n",
+    "!mv /content/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth\n",
+    "\n",
+    "!echo \"删除完成\"\n",
+    "!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "QhSiPTVPoIRh"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 清除项目下所有文件，只留选中的模型（慎点，仔细看代码）\n",
+    "# @markdown 模型名\n",
+    "MODELNAME = \"lulu\"  # @param {type:\"string\"}\n",
+    "# @markdown 选中模型epoch\n",
+    "MODELEPOCH = 9600  # @param {type:\"integer\"}\n",
+    "\n",
+    "!echo \"备份选中的模型。。。\"\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/{MODELNAME}_D_{MODELEPOCH}.pth\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/{MODELNAME}_G_{MODELEPOCH}.pth\n",
+    "\n",
+    "!echo \"正��删除。。。\"\n",
+    "!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}\n",
+    "!rm -rf /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/*\n",
+    "\n",
+    "!echo \"恢复选中的模型。。。\"\n",
+    "!mv /content/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth\n",
+    "!mv /content/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth\n",
+    "\n",
+    "!echo \"删除完成\"\n",
+    "!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}"
+   ]
+  }
+ ],
+ "metadata": {
+  "accelerator": "GPU",
+  "colab": {
+   "private_outputs": true,
+   "provenance": []
+  },
+  "gpuClass": "standard",
+  "kernelspec": {
+   "display_name": "Python 3",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}

Retrieval_based_Voice_Conversion_WebUI_v2.ipynb

@@ -0,0 +1,422 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# [Retrieval-based-Voice-Conversion-WebUI](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI) Training notebook"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "ZFFCx5J80SGa"
+   },
+   "source": [
+    "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/main/Retrieval_based_Voice_Conversion_WebUI_v2.ipynb)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "GmFP6bN9dvOq"
+   },
+   "outputs": [],
+   "source": [
+    "# @title #查看显卡\n",
+    "!nvidia-smi"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "jwu07JgqoFON"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 挂载谷歌云盘\n",
+    "\n",
+    "from google.colab import drive\n",
+    "\n",
+    "drive.mount(\"/content/drive\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "wjddIFr1oS3W"
+   },
+   "outputs": [],
+   "source": [
+    "# @title #安装依赖\n",
+    "!apt-get -y install build-essential python3-dev ffmpeg\n",
+    "!pip3 install --upgrade setuptools wheel\n",
+    "!pip3 install --upgrade pip\n",
+    "!pip3 install faiss-cpu==1.7.2 fairseq gradio==3.14.0 ffmpeg ffmpeg-python praat-parselmouth pyworld numpy==1.23.5 numba==0.56.4 librosa==0.9.2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "ge_97mfpgqTm"
+   },
+   "outputs": [],
+   "source": [
+    "# @title #克隆仓库\n",
+    "\n",
+    "!mkdir Retrieval-based-Voice-Conversion-WebUI\n",
+    "%cd /content/Retrieval-based-Voice-Conversion-WebUI\n",
+    "!git init\n",
+    "!git remote add origin https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI.git\n",
+    "!git fetch origin cfd984812804ddc9247d65b14c82cd32e56c1133 --depth=1\n",
+    "!git reset --hard FETCH_HEAD"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "BLDEZADkvlw1"
+   },
+   "outputs": [],
+   "source": [
+    "# @title #更新仓库（一般无需执行）\n",
+    "!git pull"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "pqE0PrnuRqI2"
+   },
+   "outputs": [],
+   "source": [
+    "# @title #安装aria2\n",
+    "!apt -y install -qq aria2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "UG3XpUwEomUz"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 下载底模\n",
+    "\n",
+    "# v1\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o D32k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o D40k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o D48k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/G32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o G32k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/G40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o G40k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/G48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o G48k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0D32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0D32k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0D40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0D40k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0D48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0D48k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0G32k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0G40k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0G48k.pth\n",
+    "\n",
+    "# v2\n",
+    "# !aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/D32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o D32k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/D40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o D40k.pth\n",
+    "# !aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/D48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o D48k.pth\n",
+    "# !aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/G32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o G32k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/G40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o G40k.pth\n",
+    "# !aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/G48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o G48k.pth\n",
+    "# !aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0D32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o f0D32k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0D40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o f0D40k.pth\n",
+    "# !aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0D48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o f0D48k.pth\n",
+    "# !aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0G32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o f0G32k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0G40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o f0G40k.pth\n",
+    "# !aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0G48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o f0G48k.pth"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "HugjmZqZRuiF"
+   },
+   "outputs": [],
+   "source": [
+    "# @title #下载人声分离模型\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP2-人声vocals+非人声instrumentals.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/uvr5_weights -o HP2-人声vocals+非人声instrumentals.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP5-主旋律人声vocals+其他instrumentals.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/uvr5_weights -o HP5-主旋律人声vocals+其他instrumentals.pth"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "2RCaT9FTR0ej"
+   },
+   "outputs": [],
+   "source": [
+    "# @title #下载hubert_base\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/hubert_base.pt -d /content/Retrieval-based-Voice-Conversion-WebUI -o hubert_base.pt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# @title #下载rmvpe模型\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/rmvpe.pt -d /content/Retrieval-based-Voice-Conversion-WebUI -o rmvpe.pt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "Mwk7Q0Loqzjx"
+   },
+   "outputs": [],
+   "source": [
+    "# @title #从谷歌云盘加载打包好的数据集到/content/dataset\n",
+    "\n",
+    "# @markdown 数据集位置\n",
+    "DATASET = (\n",
+    "    \"/content/drive/MyDrive/dataset/lulu20230327_32k.zip\"  # @param {type:\"string\"}\n",
+    ")\n",
+    "\n",
+    "!mkdir -p /content/dataset\n",
+    "!unzip -d /content/dataset -B {DATASET}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "PDlFxWHWEynD"
+   },
+   "outputs": [],
+   "source": [
+    "# @title #重命名数据集中的重名文件\n",
+    "!ls -a /content/dataset/\n",
+    "!rename 's/(\\w+)\\.(\\w+)~(\\d*)/$1_$3.$2/' /content/dataset/*.*~*"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "7vh6vphDwO0b"
+   },
+   "outputs": [],
+   "source": [
+    "# @title #启动webui\n",
+    "%cd /content/Retrieval-based-Voice-Conversion-WebUI\n",
+    "# %load_ext tensorboard\n",
+    "# %tensorboard --logdir /content/Retrieval-based-Voice-Conversion-WebUI/logs\n",
+    "!python3 infer-web.py --colab --pycmd python3"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "FgJuNeAwx5Y_"
+   },
+   "outputs": [],
+   "source": [
+    "# @title #手动将训练后的模型文件备份到谷歌云盘\n",
+    "# @markdown #需要自己查看logs文件夹下模型的文件名，手动修改下方命令末尾的文件名\n",
+    "\n",
+    "# @markdown #模型名\n",
+    "MODELNAME = \"lulu\"  # @param {type:\"string\"}\n",
+    "# @markdown #模型epoch\n",
+    "MODELEPOCH = 9600  # @param {type:\"integer\"}\n",
+    "\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/drive/MyDrive/{MODELNAME}_D_{MODELEPOCH}.pth\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/drive/MyDrive/{MODELNAME}_G_{MODELEPOCH}.pth\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/added_*.index /content/drive/MyDrive/\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/total_*.npy /content/drive/MyDrive/\n",
+    "\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/weights/{MODELNAME}.pth /content/drive/MyDrive/{MODELNAME}{MODELEPOCH}.pth"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "OVQoLQJXS7WX"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 从谷歌云盘恢复pth\n",
+    "# @markdown 需要自己查看logs文件夹下模型的文件名，手动修改下方命令末尾的文件名\n",
+    "\n",
+    "# @markdown 模型名\n",
+    "MODELNAME = \"lulu\"  # @param {type:\"string\"}\n",
+    "# @markdown 模型epoch\n",
+    "MODELEPOCH = 7500  # @param {type:\"integer\"}\n",
+    "\n",
+    "!mkdir -p /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}\n",
+    "\n",
+    "!cp /content/drive/MyDrive/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth\n",
+    "!cp /content/drive/MyDrive/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth\n",
+    "!cp /content/drive/MyDrive/*.index /content/\n",
+    "!cp /content/drive/MyDrive/*.npy /content/\n",
+    "!cp /content/drive/MyDrive/{MODELNAME}{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/weights/{MODELNAME}.pth"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "ZKAyuKb9J6dz"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 手动预处理（不推荐）\n",
+    "# @markdown 模型名\n",
+    "MODELNAME = \"lulu\"  # @param {type:\"string\"}\n",
+    "# @markdown 采样率\n",
+    "BITRATE = 48000  # @param {type:\"integer\"}\n",
+    "# @markdown 使用的进程数\n",
+    "THREADCOUNT = 8  # @param {type:\"integer\"}\n",
+    "\n",
+    "!python3 trainset_preprocess_pipeline_print.py /content/dataset {BITRATE} {THREADCOUNT} logs/{MODELNAME} True"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "CrxJqzAUKmPJ"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 手动提取特征（不推荐）\n",
+    "# @markdown 模型名\n",
+    "MODELNAME = \"lulu\"  # @param {type:\"string\"}\n",
+    "# @markdown 使用的进程数\n",
+    "THREADCOUNT = 8  # @param {type:\"integer\"}\n",
+    "# @markdown 音高提取算法\n",
+    "ALGO = \"harvest\"  # @param {type:\"string\"}\n",
+    "\n",
+    "!python3 extract_f0_print.py logs/{MODELNAME} {THREADCOUNT} {ALGO}\n",
+    "\n",
+    "!python3 extract_feature_print.py cpu 1 0 0 logs/{MODELNAME}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "IMLPLKOaKj58"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 手动训练（不推荐）\n",
+    "# @markdown 模型名\n",
+    "MODELNAME = \"lulu\"  # @param {type:\"string\"}\n",
+    "# @markdown 使用的GPU\n",
+    "USEGPU = \"0\"  # @param {type:\"string\"}\n",
+    "# @markdown 批大小\n",
+    "BATCHSIZE = 32  # @param {type:\"integer\"}\n",
+    "# @markdown 停止的epoch\n",
+    "MODELEPOCH = 3200  # @param {type:\"integer\"}\n",
+    "# @markdown 保存epoch间隔\n",
+    "EPOCHSAVE = 100  # @param {type:\"integer\"}\n",
+    "# @markdown 采样率\n",
+    "MODELSAMPLE = \"48k\"  # @param {type:\"string\"}\n",
+    "# @markdown 是否缓存训练集\n",
+    "CACHEDATA = 1  # @param {type:\"integer\"}\n",
+    "# @markdown 是否仅保存最新的ckpt文件\n",
+    "ONLYLATEST = 0  # @param {type:\"integer\"}\n",
+    "\n",
+    "!python3 train_nsf_sim_cache_sid_load_pretrain.py -e lulu -sr {MODELSAMPLE} -f0 1 -bs {BATCHSIZE} -g {USEGPU} -te {MODELEPOCH} -se {EPOCHSAVE} -pg pretrained/f0G{MODELSAMPLE}.pth -pd pretrained/f0D{MODELSAMPLE}.pth -l {ONLYLATEST} -c {CACHEDATA}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "haYA81hySuDl"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 删除其它pth，只留选中的（慎点，仔细看代码）\n",
+    "# @markdown 模型名\n",
+    "MODELNAME = \"lulu\"  # @param {type:\"string\"}\n",
+    "# @markdown 选中模型epoch\n",
+    "MODELEPOCH = 9600  # @param {type:\"integer\"}\n",
+    "\n",
+    "!echo \"备份选中的模型。。。\"\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/{MODELNAME}_D_{MODELEPOCH}.pth\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/{MODELNAME}_G_{MODELEPOCH}.pth\n",
+    "\n",
+    "!echo \"正在删除。。。\"\n",
+    "!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}\n",
+    "!rm /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/*.pth\n",
+    "\n",
+    "!echo \"恢复选中的模型。。。\"\n",
+    "!mv /content/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth\n",
+    "!mv /content/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth\n",
+    "\n",
+    "!echo \"删除完成\"\n",
+    "!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "QhSiPTVPoIRh"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 清除项目下所有文件，只留选中的模型（慎点，仔细看代码）\n",
+    "# @markdown 模型名\n",
+    "MODELNAME = \"lulu\"  # @param {type:\"string\"}\n",
+    "# @markdown 选中模型epoch\n",
+    "MODELEPOCH = 9600  # @param {type:\"integer\"}\n",
+    "\n",
+    "!echo \"备份选中的模型。。。\"\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/{MODELNAME}_D_{MODELEPOCH}.pth\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/{MODELNAME}_G_{MODELEPOCH}.pth\n",
+    "\n",
+    "!echo \"正在删除。。。\"\n",
+    "!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}\n",
+    "!rm -rf /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/*\n",
+    "\n",
+    "!echo \"恢复选中的模型。。。\"\n",
+    "!mv /content/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth\n",
+    "!mv /content/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth\n",
+    "\n",
+    "!echo \"删除完成\"\n",
+    "!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}"
+   ]
+  }
+ ],
+ "metadata": {
+  "accelerator": "GPU",
+  "colab": {
+   "private_outputs": true,
+   "provenance": []
+  },
+  "gpuClass": "standard",
+  "kernelspec": {
+   "display_name": "Python 3",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}

app.py

@@ -0,0 +1,1449 @@
+import os, sys
+import datetime, subprocess
+from mega import Mega
+now_dir = os.getcwd()
+sys.path.append(now_dir)
+import logging
+import shutil
+import threading
+import traceback
+import warnings
+from random import shuffle
+from subprocess import Popen
+from time import sleep
+import json
+import pathlib
+
+import fairseq
+import faiss
+import gradio as gr
+import numpy as np
+import torch
+from dotenv import load_dotenv
+from sklearn.cluster import MiniBatchKMeans
+
+from configs.config import Config
+from i18n.i18n import I18nAuto
+from infer.lib.train.process_ckpt import (
+    change_info,
+    extract_small_model,
+    merge,
+    show_info,
+)
+from infer.modules.uvr5.modules import uvr
+from infer.modules.vc.modules import VC
+logging.getLogger("numba").setLevel(logging.WARNING)
+
+logger = logging.getLogger(__name__)
+
+tmp = os.path.join(now_dir, "TEMP")
+shutil.rmtree(tmp, ignore_errors=True)
+shutil.rmtree("%s/runtime/Lib/site-packages/infer_pack" % (now_dir), ignore_errors=True)
+shutil.rmtree("%s/runtime/Lib/site-packages/uvr5_pack" % (now_dir), ignore_errors=True)
+os.makedirs(tmp, exist_ok=True)
+os.makedirs(os.path.join(now_dir, "logs"), exist_ok=True)
+os.makedirs(os.path.join(now_dir, "assets/weights"), exist_ok=True)
+os.environ["TEMP"] = tmp
+warnings.filterwarnings("ignore")
+torch.manual_seed(114514)
+
+
+load_dotenv()
+config = Config()
+vc = VC(config)
+
+if config.dml == True:
+
+    def forward_dml(ctx, x, scale):
+        ctx.scale = scale
+        res = x.clone().detach()
+        return res
+
+    fairseq.modules.grad_multiply.GradMultiply.forward = forward_dml
+i18n = I18nAuto()
+logger.info(i18n)
+# 判断是否有能用来训练和加速推理的N卡
+ngpu = torch.cuda.device_count()
+gpu_infos = []
+mem = []
+if_gpu_ok = False
+
+if torch.cuda.is_available() or ngpu != 0:
+    for i in range(ngpu):
+        gpu_name = torch.cuda.get_device_name(i)
+        if any(
+            value in gpu_name.upper()
+            for value in [
+                "10",
+                "16",
+                "20",
+                "30",
+                "40",
+                "A2",
+                "A3",
+                "A4",
+                "P4",
+                "A50",
+                "500",
+                "A60",
+                "70",
+                "80",
+                "90",
+                "M4",
+                "T4",
+                "TITAN",
+            ]
+        ):
+            # A10#A100#V100#A40#P40#M40#K80#A4500
+            if_gpu_ok = True  # 至少有一张能用的N卡
+            gpu_infos.append("%s\t%s" % (i, gpu_name))
+            mem.append(
+                int(
+                    torch.cuda.get_device_properties(i).total_memory
+                    / 1024
+                    / 1024
+                    / 1024
+                    + 0.4
+                )
+            )
+if if_gpu_ok and len(gpu_infos) > 0:
+    gpu_info = "\n".join(gpu_infos)
+    default_batch_size = min(mem) // 2
+else:
+    gpu_info = i18n("很遗憾您这没有能用的显卡来支持您训练")
+    default_batch_size = 1
+gpus = "-".join([i[0] for i in gpu_infos])
+
+
+class ToolButton(gr.Button, gr.components.FormComponent):
+    """Small button with single emoji as text, fits inside gradio forms"""
+
+    def __init__(self, **kwargs):
+        super().__init__(variant="tool", **kwargs)
+
+    def get_block_name(self):
+        return "button"
+
+
+weight_root = os.getenv("weight_root")
+weight_uvr5_root = os.getenv("weight_uvr5_root")
+index_root = os.getenv("index_root")
+
+names = []
+for name in os.listdir(weight_root):
+    if name.endswith(".pth"):
+        names.append(name)
+index_paths = []
+for root, dirs, files in os.walk(index_root, topdown=False):
+    for name in files:
+        if name.endswith(".index") and "trained" not in name:
+            index_paths.append("%s/%s" % (root, name))
+uvr5_names = []
+for name in os.listdir(weight_uvr5_root):
+    if name.endswith(".pth") or "onnx" in name:
+        uvr5_names.append(name.replace(".pth", ""))
+
+
+def change_choices():
+    names = []
+    for name in os.listdir(weight_root):
+        if name.endswith(".pth"):
+            names.append(name)
+    index_paths = []
+    for root, dirs, files in os.walk(index_root, topdown=False):
+        for name in files:
+            if name.endswith(".index") and "trained" not in name:
+                index_paths.append("%s/%s" % (root, name))
+    audio_files=[]
+    for filename in os.listdir("./audios"):
+        if filename.endswith(('.wav','.mp3','.ogg')):
+            audio_files.append('./audios/'+filename)
+    return {"choices": sorted(names), "__type__": "update"}, {
+        "choices": sorted(index_paths),
+        "__type__": "update",
+    }, {"choices": sorted(audio_files), "__type__": "update"}
+
+def clean():
+    return {"value": "", "__type__": "update"}
+
+
+def export_onnx():
+    from infer.modules.onnx.export import export_onnx as eo
+
+    eo()
+
+
+sr_dict = {
+    "32k": 32000,
+    "40k": 40000,
+    "48k": 48000,
+}
+
+
+def if_done(done, p):
+    while 1:
+        if p.poll() is None:
+            sleep(0.5)
+        else:
+            break
+    done[0] = True
+
+
+def if_done_multi(done, ps):
+    while 1:
+        # poll==None代表进程未结束
+        # 只要有一个进程未结束都不停
+        flag = 1
+        for p in ps:
+            if p.poll() is None:
+                flag = 0
+                sleep(0.5)
+                break
+        if flag == 1:
+            break
+    done[0] = True
+
+
+def preprocess_dataset(trainset_dir, exp_dir, sr, n_p):
+    sr = sr_dict[sr]
+    os.makedirs("%s/logs/%s" % (now_dir, exp_dir), exist_ok=True)
+    f = open("%s/logs/%s/preprocess.log" % (now_dir, exp_dir), "w")
+    f.close()
+    per = 3.0 if config.is_half else 3.7
+    cmd = '"%s" infer/modules/train/preprocess.py "%s" %s %s "%s/logs/%s" %s %.1f' % (
+        config.python_cmd,
+        trainset_dir,
+        sr,
+        n_p,
+        now_dir,
+        exp_dir,
+        config.noparallel,
+        per,
+    )
+    logger.info(cmd)
+    p = Popen(cmd, shell=True)  # , stdin=PIPE, stdout=PIPE,stderr=PIPE,cwd=now_dir
+    ###煞笔gr, popen read都非得全跑完了再一次性读取, 不用gr就正常读一句输出一句;只能额外弄出一个文本流定时读
+    done = [False]
+    threading.Thread(
+        target=if_done,
+        args=(
+            done,
+            p,
+        ),
+    ).start()
+    while 1:
+        with open("%s/logs/%s/preprocess.log" % (now_dir, exp_dir), "r") as f:
+            yield (f.read())
+        sleep(1)
+        if done[0]:
+            break
+    with open("%s/logs/%s/preprocess.log" % (now_dir, exp_dir), "r") as f:
+        log = f.read()
+    logger.info(log)
+    yield log
+
+
+# but2.click(extract_f0,[gpus6,np7,f0method8,if_f0_3,trainset_dir4],[info2])
+def extract_f0_feature(gpus, n_p, f0method, if_f0, exp_dir, version19, gpus_rmvpe):
+    gpus = gpus.split("-")
+    os.makedirs("%s/logs/%s" % (now_dir, exp_dir), exist_ok=True)
+    f = open("%s/logs/%s/extract_f0_feature.log" % (now_dir, exp_dir), "w")
+    f.close()
+    if if_f0:
+        if f0method != "rmvpe_gpu":
+            cmd = (
+                '"%s" infer/modules/train/extract/extract_f0_print.py "%s/logs/%s" %s %s'
+                % (
+                    config.python_cmd,
+                    now_dir,
+                    exp_dir,
+                    n_p,
+                    f0method,
+                )
+            )
+            logger.info(cmd)
+            p = Popen(
+                cmd, shell=True, cwd=now_dir
+            )  # , stdin=PIPE, stdout=PIPE,stderr=PIPE
+            ###煞笔gr, popen read都非得全跑完了再一次性读取, 不用gr就正常读一句输出一句;只能额外弄出一个文本流定时读
+            done = [False]
+            threading.Thread(
+                target=if_done,
+                args=(
+                    done,
+                    p,
+                ),
+            ).start()
+        else:
+            if gpus_rmvpe != "-":
+                gpus_rmvpe = gpus_rmvpe.split("-")
+                leng = len(gpus_rmvpe)
+                ps = []
+                for idx, n_g in enumerate(gpus_rmvpe):
+                    cmd = (
+                        '"%s" infer/modules/train/extract/extract_f0_rmvpe.py %s %s %s "%s/logs/%s" %s '
+                        % (
+                            config.python_cmd,
+                            leng,
+                            idx,
+                            n_g,
+                            now_dir,
+                            exp_dir,
+                            config.is_half,
+                        )
+                    )
+                    logger.info(cmd)
+                    p = Popen(
+                        cmd, shell=True, cwd=now_dir
+                    )  # , shell=True, stdin=PIPE, stdout=PIPE, stderr=PIPE, cwd=now_dir
+                    ps.append(p)
+                ###煞笔gr, popen read都非得全跑完了再一次性读取, 不用gr就正常读一句输出一句;只能额外弄出一个文本流定时读
+                done = [False]
+                threading.Thread(
+                    target=if_done_multi,  #
+                    args=(
+                        done,
+                        ps,
+                    ),
+                ).start()
+            else:
+                cmd = (
+                    config.python_cmd
+                    + ' infer/modules/train/extract/extract_f0_rmvpe_dml.py "%s/logs/%s" '
+                    % (
+                        now_dir,
+                        exp_dir,
+                    )
+                )
+                logger.info(cmd)
+                p = Popen(
+                    cmd, shell=True, cwd=now_dir
+                )  # , shell=True, stdin=PIPE, stdout=PIPE, stderr=PIPE, cwd=now_dir
+                p.wait()
+                done = [True]
+        while 1:
+            with open(
+                "%s/logs/%s/extract_f0_feature.log" % (now_dir, exp_dir), "r"
+            ) as f:
+                yield (f.read())
+            sleep(1)
+            if done[0]:
+                break
+        with open("%s/logs/%s/extract_f0_feature.log" % (now_dir, exp_dir), "r") as f:
+            log = f.read()
+        logger.info(log)
+        yield log
+    ####对不同part分别开多进程
+    """
+    n_part=int(sys.argv[1])
+    i_part=int(sys.argv[2])
+    i_gpu=sys.argv[3]
+    exp_dir=sys.argv[4]
+    os.environ["CUDA_VISIBLE_DEVICES"]=str(i_gpu)
+    """
+    leng = len(gpus)
+    ps = []
+    for idx, n_g in enumerate(gpus):
+        cmd = (
+            '"%s" infer/modules/train/extract_feature_print.py %s %s %s %s "%s/logs/%s" %s'
+            % (
+                config.python_cmd,
+                config.device,
+                leng,
+                idx,
+                n_g,
+                now_dir,
+                exp_dir,
+                version19,
+            )
+        )
+        logger.info(cmd)
+        p = Popen(
+            cmd, shell=True, cwd=now_dir
+        )  # , shell=True, stdin=PIPE, stdout=PIPE, stderr=PIPE, cwd=now_dir
+        ps.append(p)
+    ###煞笔gr, popen read都非得全跑完了再一次性读取, 不用gr就正常读一句输出一句;只能额外弄出一个文本流定时读
+    done = [False]
+    threading.Thread(
+        target=if_done_multi,
+        args=(
+            done,
+            ps,
+        ),
+    ).start()
+    while 1:
+        with open("%s/logs/%s/extract_f0_feature.log" % (now_dir, exp_dir), "r") as f:
+            yield (f.read())
+        sleep(1)
+        if done[0]:
+            break
+    with open("%s/logs/%s/extract_f0_feature.log" % (now_dir, exp_dir), "r") as f:
+        log = f.read()
+    logger.info(log)
+    yield log
+
+
+def get_pretrained_models(path_str, f0_str, sr2):
+    if_pretrained_generator_exist = os.access(
+        "assets/pretrained%s/%sG%s.pth" % (path_str, f0_str, sr2), os.F_OK
+    )
+    if_pretrained_discriminator_exist = os.access(
+        "assets/pretrained%s/%sD%s.pth" % (path_str, f0_str, sr2), os.F_OK
+    )
+    if not if_pretrained_generator_exist:
+        logger.warn(
+            "assets/pretrained%s/%sG%s.pth not exist, will not use pretrained model",
+            path_str,
+            f0_str,
+            sr2,
+        )
+    if not if_pretrained_discriminator_exist:
+        logger.warn(
+            "assets/pretrained%s/%sD%s.pth not exist, will not use pretrained model",
+            path_str,
+            f0_str,
+            sr2,
+        )
+    return (
+        "assets/pretrained%s/%sG%s.pth" % (path_str, f0_str, sr2)
+        if if_pretrained_generator_exist
+        else "",
+        "assets/pretrained%s/%sD%s.pth" % (path_str, f0_str, sr2)
+        if if_pretrained_discriminator_exist
+        else "",
+    )
+
+
+def change_sr2(sr2, if_f0_3, version19):
+    path_str = "" if version19 == "v1" else "_v2"
+    f0_str = "f0" if if_f0_3 else ""
+    return get_pretrained_models(path_str, f0_str, sr2)
+
+
+def change_version19(sr2, if_f0_3, version19):
+    path_str = "" if version19 == "v1" else "_v2"
+    if sr2 == "32k" and version19 == "v1":
+        sr2 = "40k"
+    to_return_sr2 = (
+        {"choices": ["40k", "48k"], "__type__": "update", "value": sr2}
+        if version19 == "v1"
+        else {"choices": ["40k", "48k", "32k"], "__type__": "update", "value": sr2}
+    )
+    f0_str = "f0" if if_f0_3 else ""
+    return (
+        *get_pretrained_models(path_str, f0_str, sr2),
+        to_return_sr2,
+    )
+
+
+def change_f0(if_f0_3, sr2, version19):  # f0method8,pretrained_G14,pretrained_D15
+    path_str = "" if version19 == "v1" else "_v2"
+    return (
+        {"visible": if_f0_3, "__type__": "update"},
+        *get_pretrained_models(path_str, "f0", sr2),
+    )
+
+
+# but3.click(click_train,[exp_dir1,sr2,if_f0_3,save_epoch10,total_epoch11,batch_size12,if_save_latest13,pretrained_G14,pretrained_D15,gpus16])
+def click_train(
+    exp_dir1,
+    sr2,
+    if_f0_3,
+    spk_id5,
+    save_epoch10,
+    total_epoch11,
+    batch_size12,
+    if_save_latest13,
+    pretrained_G14,
+    pretrained_D15,
+    gpus16,
+    if_cache_gpu17,
+    if_save_every_weights18,
+    version19,
+):
+    # 生成filelist
+    exp_dir = "%s/logs/%s" % (now_dir, exp_dir1)
+    os.makedirs(exp_dir, exist_ok=True)
+    gt_wavs_dir = "%s/0_gt_wavs" % (exp_dir)
+    feature_dir = (
+        "%s/3_feature256" % (exp_dir)
+        if version19 == "v1"
+        else "%s/3_feature768" % (exp_dir)
+    )
+    if if_f0_3:
+        f0_dir = "%s/2a_f0" % (exp_dir)
+        f0nsf_dir = "%s/2b-f0nsf" % (exp_dir)
+        names = (
+            set([name.split(".")[0] for name in os.listdir(gt_wavs_dir)])
+            & set([name.split(".")[0] for name in os.listdir(feature_dir)])
+            & set([name.split(".")[0] for name in os.listdir(f0_dir)])
+            & set([name.split(".")[0] for name in os.listdir(f0nsf_dir)])
+        )
+    else:
+        names = set([name.split(".")[0] for name in os.listdir(gt_wavs_dir)]) & set(
+            [name.split(".")[0] for name in os.listdir(feature_dir)]
+        )
+    opt = []
+    for name in names:
+        if if_f0_3:
+            opt.append(
+                "%s/%s.wav|%s/%s.npy|%s/%s.wav.npy|%s/%s.wav.npy|%s"
+                % (
+                    gt_wavs_dir.replace("\\", "\\\\"),
+                    name,
+                    feature_dir.replace("\\", "\\\\"),
+                    name,
+                    f0_dir.replace("\\", "\\\\"),
+                    name,
+                    f0nsf_dir.replace("\\", "\\\\"),
+                    name,
+                    spk_id5,
+                )
+            )
+        else:
+            opt.append(
+                "%s/%s.wav|%s/%s.npy|%s"
+                % (
+                    gt_wavs_dir.replace("\\", "\\\\"),
+                    name,
+                    feature_dir.replace("\\", "\\\\"),
+                    name,
+                    spk_id5,
+                )
+            )
+    fea_dim = 256 if version19 == "v1" else 768
+    if if_f0_3:
+        for _ in range(2):
+            opt.append(
+                "%s/logs/mute/0_gt_wavs/mute%s.wav|%s/logs/mute/3_feature%s/mute.npy|%s/logs/mute/2a_f0/mute.wav.npy|%s/logs/mute/2b-f0nsf/mute.wav.npy|%s"
+                % (now_dir, sr2, now_dir, fea_dim, now_dir, now_dir, spk_id5)
+            )
+    else:
+        for _ in range(2):
+            opt.append(
+                "%s/logs/mute/0_gt_wavs/mute%s.wav|%s/logs/mute/3_feature%s/mute.npy|%s"
+                % (now_dir, sr2, now_dir, fea_dim, spk_id5)
+            )
+    shuffle(opt)
+    with open("%s/filelist.txt" % exp_dir, "w") as f:
+        f.write("\n".join(opt))
+    logger.debug("Write filelist done")
+    # 生成config#无需生成config
+    # cmd = python_cmd + " train_nsf_sim_cache_sid_load_pretrain.py -e mi-test -sr 40k -f0 1 -bs 4 -g 0 -te 10 -se 5 -pg pretrained/f0G40k.pth -pd pretrained/f0D40k.pth -l 1 -c 0"
+    logger.info("Use gpus: %s", str(gpus16))
+    if pretrained_G14 == "":
+        logger.info("No pretrained Generator")
+    if pretrained_D15 == "":
+        logger.info("No pretrained Discriminator")
+    if version19 == "v1" or sr2 == "40k":
+        config_path = "v1/%s.json" % sr2
+    else:
+        config_path = "v2/%s.json" % sr2
+    config_save_path = os.path.join(exp_dir, "config.json")
+    if not pathlib.Path(config_save_path).exists():
+        with open(config_save_path, "w", encoding="utf-8") as f:
+            json.dump(
+                config.json_config[config_path],
+                f,
+                ensure_ascii=False,
+                indent=4,
+                sort_keys=True,
+            )
+            f.write("\n")
+    if gpus16:
+        cmd = (
+            '"%s" infer/modules/train/train.py -e "%s" -sr %s -f0 %s -bs %s -g %s -te %s -se %s %s %s -l %s -c %s -sw %s -v %s'
+            % (
+                config.python_cmd,
+                exp_dir1,
+                sr2,
+                1 if if_f0_3 else 0,
+                batch_size12,
+                gpus16,
+                total_epoch11,
+                save_epoch10,
+                "-pg %s" % pretrained_G14 if pretrained_G14 != "" else "",
+                "-pd %s" % pretrained_D15 if pretrained_D15 != "" else "",
+                1 if if_save_latest13 == i18n("是") else 0,
+                1 if if_cache_gpu17 == i18n("是") else 0,
+                1 if if_save_every_weights18 == i18n("是") else 0,
+                version19,
+            )
+        )
+    else:
+        cmd = (
+            '"%s" infer/modules/train/train.py -e "%s" -sr %s -f0 %s -bs %s -te %s -se %s %s %s -l %s -c %s -sw %s -v %s'
+            % (
+                config.python_cmd,
+                exp_dir1,
+                sr2,
+                1 if if_f0_3 else 0,
+                batch_size12,
+                total_epoch11,
+                save_epoch10,
+                "-pg %s" % pretrained_G14 if pretrained_G14 != "" else "",
+                "-pd %s" % pretrained_D15 if pretrained_D15 != "" else "",
+                1 if if_save_latest13 == i18n("是") else 0,
+                1 if if_cache_gpu17 == i18n("是") else 0,
+                1 if if_save_every_weights18 == i18n("是") else 0,
+                version19,
+            )
+        )
+    logger.info(cmd)
+    p = Popen(cmd, shell=True, cwd=now_dir)
+    p.wait()
+    return "训练结束, 您可查看控制台训练日志或实验文件夹下的train.log"
+
+
+# but4.click(train_index, [exp_dir1], info3)
+def train_index(exp_dir1, version19):
+    # exp_dir = "%s/logs/%s" % (now_dir, exp_dir1)
+    exp_dir = "logs/%s" % (exp_dir1)
+    os.makedirs(exp_dir, exist_ok=True)
+    feature_dir = (
+        "%s/3_feature256" % (exp_dir)
+        if version19 == "v1"
+        else "%s/3_feature768" % (exp_dir)
+    )
+    if not os.path.exists(feature_dir):
+        return "请先进行特征提取!"
+    listdir_res = list(os.listdir(feature_dir))
+    if len(listdir_res) == 0:
+        return "请先进行特征提取！"
+    infos = []
+    npys = []
+    for name in sorted(listdir_res):
+        phone = np.load("%s/%s" % (feature_dir, name))
+        npys.append(phone)
+    big_npy = np.concatenate(npys, 0)
+    big_npy_idx = np.arange(big_npy.shape[0])
+    np.random.shuffle(big_npy_idx)
+    big_npy = big_npy[big_npy_idx]
+    if big_npy.shape[0] > 2e5:
+        infos.append("Trying doing kmeans %s shape to 10k centers." % big_npy.shape[0])
+        yield "\n".join(infos)
+        try:
+            big_npy = (
+                MiniBatchKMeans(
+                    n_clusters=10000,
+                    verbose=True,
+                    batch_size=256 * config.n_cpu,
+                    compute_labels=False,
+                    init="random",
+                )
+                .fit(big_npy)
+                .cluster_centers_
+            )
+        except:
+            info = traceback.format_exc()
+            logger.info(info)
+            infos.append(info)
+            yield "\n".join(infos)
+
+    np.save("%s/total_fea.npy" % exp_dir, big_npy)
+    n_ivf = min(int(16 * np.sqrt(big_npy.shape[0])), big_npy.shape[0] // 39)
+    infos.append("%s,%s" % (big_npy.shape, n_ivf))
+    yield "\n".join(infos)
+    index = faiss.index_factory(256 if version19 == "v1" else 768, "IVF%s,Flat" % n_ivf)
+    # index = faiss.index_factory(256if version19=="v1"else 768, "IVF%s,PQ128x4fs,RFlat"%n_ivf)
+    infos.append("training")
+    yield "\n".join(infos)
+    index_ivf = faiss.extract_index_ivf(index)  #
+    index_ivf.nprobe = 1
+    index.train(big_npy)
+    faiss.write_index(
+        index,
+        "%s/trained_IVF%s_Flat_nprobe_%s_%s_%s.index"
+        % (exp_dir, n_ivf, index_ivf.nprobe, exp_dir1, version19),
+    )
+
+    infos.append("adding")
+    yield "\n".join(infos)
+    batch_size_add = 8192
+    for i in range(0, big_npy.shape[0], batch_size_add):
+        index.add(big_npy[i : i + batch_size_add])
+    faiss.write_index(
+        index,
+        "%s/added_IVF%s_Flat_nprobe_%s_%s_%s.index"
+        % (exp_dir, n_ivf, index_ivf.nprobe, exp_dir1, version19),
+    )
+    infos.append(
+        "成功构建索引，added_IVF%s_Flat_nprobe_%s_%s_%s.index"
+        % (n_ivf, index_ivf.nprobe, exp_dir1, version19)
+    )
+    # faiss.write_index(index, '%s/added_IVF%s_Flat_FastScan_%s.index'%(exp_dir,n_ivf,version19))
+    # infos.append("成功构建索引，added_IVF%s_Flat_FastScan_%s.index"%(n_ivf,version19))
+    yield "\n".join(infos)
+
+
+# but5.click(train1key, [exp_dir1, sr2, if_f0_3, trainset_dir4, spk_id5, gpus6, np7, f0method8, save_epoch10, total_epoch11, batch_size12, if_save_latest13, pretrained_G14, pretrained_D15, gpus16, if_cache_gpu17], info3)
+def train1key(
+    exp_dir1,
+    sr2,
+    if_f0_3,
+    trainset_dir4,
+    spk_id5,
+    np7,
+    f0method8,
+    save_epoch10,
+    total_epoch11,
+    batch_size12,
+    if_save_latest13,
+    pretrained_G14,
+    pretrained_D15,
+    gpus16,
+    if_cache_gpu17,
+    if_save_every_weights18,
+    version19,
+    gpus_rmvpe,
+):
+    infos = []
+
+    def get_info_str(strr):
+        infos.append(strr)
+        return "\n".join(infos)
+
+    ####### step1:处理数据
+    yield get_info_str(i18n("step1:正在处理数据"))
+    [get_info_str(_) for _ in preprocess_dataset(trainset_dir4, exp_dir1, sr2, np7)]
+
+    ####### step2a:提取音高
+    yield get_info_str(i18n("step2:正在提取音高&正在提取特征"))
+    [
+        get_info_str(_)
+        for _ in extract_f0_feature(
+            gpus16, np7, f0method8, if_f0_3, exp_dir1, version19, gpus_rmvpe
+        )
+    ]
+
+    ####### step3a:训练模型
+    yield get_info_str(i18n("step3a:正在训练模型"))
+    click_train(
+        exp_dir1,
+        sr2,
+        if_f0_3,
+        spk_id5,
+        save_epoch10,
+        total_epoch11,
+        batch_size12,
+        if_save_latest13,
+        pretrained_G14,
+        pretrained_D15,
+        gpus16,
+        if_cache_gpu17,
+        if_save_every_weights18,
+        version19,
+    )
+    yield get_info_str(i18n("训练结束, 您可查看控制台训练日志或实验文件夹下的train.log"))
+
+    ####### step3b:训练索引
+    [get_info_str(_) for _ in train_index(exp_dir1, version19)]
+    yield get_info_str(i18n("全流程结束！"))
+
+
+#                    ckpt_path2.change(change_info_,[ckpt_path2],[sr__,if_f0__])
+def change_info_(ckpt_path):
+    if not os.path.exists(ckpt_path.replace(os.path.basename(ckpt_path), "train.log")):
+        return {"__type__": "update"}, {"__type__": "update"}, {"__type__": "update"}
+    try:
+        with open(
+            ckpt_path.replace(os.path.basename(ckpt_path), "train.log"), "r"
+        ) as f:
+            info = eval(f.read().strip("\n").split("\n")[0].split("\t")[-1])
+            sr, f0 = info["sample_rate"], info["if_f0"]
+            version = "v2" if ("version" in info and info["version"] == "v2") else "v1"
+            return sr, str(f0), version
+    except:
+        traceback.print_exc()
+        return {"__type__": "update"}, {"__type__": "update"}, {"__type__": "update"}
+
+
+F0GPUVisible = config.dml == False
+
+
+def change_f0_method(f0method8):
+    if f0method8 == "rmvpe_gpu":
+        visible = F0GPUVisible
+    else:
+        visible = False
+    return {"visible": visible, "__type__": "update"}
+
+def find_model():
+    if len(names) > 0:
+        vc.get_vc(sorted(names)[0],None,None)
+        return sorted(names)[0]
+    else:
+        try:
+            gr.Info("Do not forget to choose a model.")
+        except:
+            pass
+        return ''
+    
+def find_audios(index=False):     
+    audio_files=[]
+    if not os.path.exists('./audios'): os.mkdir("./audios")
+    for filename in os.listdir("./audios"):
+        if filename.endswith(('.wav','.mp3','.ogg')):
+            audio_files.append("./audios/"+filename)
+    if index:
+        if len(audio_files) > 0: return sorted(audio_files)[0]
+        else: return ""
+    elif len(audio_files) > 0: return sorted(audio_files)
+    else: return []
+
+def get_index():
+    if find_model() != '':
+        chosen_model=sorted(names)[0].split(".")[0]
+        logs_path="./logs/"+chosen_model
+        if os.path.exists(logs_path):
+            for file in os.listdir(logs_path):
+                if file.endswith(".index"):
+                    return os.path.join(logs_path, file)
+            return ''
+        else:
+            return ''
+        
+def get_indexes():
+    indexes_list=[]
+    for dirpath, dirnames, filenames in os.walk("./logs/"):
+        for filename in filenames:
+            if filename.endswith(".index"):
+                indexes_list.append(os.path.join(dirpath,filename))
+    if len(indexes_list) > 0:
+        return indexes_list
+    else:
+        return ''
+    
+def save_wav(file):
+    try:
+        file_path=file.name
+        shutil.move(file_path,'./audios')
+        return './audios/'+os.path.basename(file_path)
+    except AttributeError:
+        try:
+            new_name = 'kpop'+datetime.datetime.now().strftime("%Y-%m-%d_%H-%M-%S")+'.wav'
+            new_path='./audios/'+new_name
+            shutil.move(file,new_path)
+            return new_path
+        except TypeError:
+            return None
+
+def download_from_url(url, model):
+    if url == '':
+        return "URL cannot be left empty."
+    if model =='':
+        return "You need to name your model. For example: My-Model"
+    url = url.strip()
+    zip_dirs = ["zips", "unzips"]
+    for directory in zip_dirs:
+        if os.path.exists(directory):
+            shutil.rmtree(directory)
+    os.makedirs("zips", exist_ok=True)
+    os.makedirs("unzips", exist_ok=True)
+    zipfile = model + '.zip'
+    zipfile_path = './zips/' + zipfile
+    try:
+        if "drive.google.com" in url:
+            subprocess.run(["gdown", url, "--fuzzy", "-O", zipfile_path])
+        elif "mega.nz" in url:
+            m = Mega()
+            m.download_url(url, './zips')
+        else:
+            subprocess.run(["wget", url, "-O", zipfile_path])
+        for filename in os.listdir("./zips"):
+            if filename.endswith(".zip"):
+                zipfile_path = os.path.join("./zips/",filename)
+                shutil.unpack_archive(zipfile_path, "./unzips", 'zip')
+            else:
+                return "No zipfile found."
+        for root, dirs, files in os.walk('./unzips'):
+            for file in files:
+                file_path = os.path.join(root, file)
+                if file.endswith(".index"):
+                    os.mkdir(f'./logs/{model}')
+                    shutil.copy2(file_path,f'./logs/{model}')
+                elif "G_" not in file and "D_" not in file and file.endswith(".pth"):
+                    shutil.copy(file_path,f'./assets/weights/{model}.pth')
+        shutil.rmtree("zips")
+        shutil.rmtree("unzips")
+        return "Success."
+    except:
+        return "There's been an error."
+
+def upload_to_dataset(files, dir):
+    if dir == '':
+        dir = './dataset/'+datetime.datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
+    if not os.path.exists(dir):
+        os.makedirs(dir)
+    for file in files:
+        path=file.name
+        shutil.copy2(path,dir)
+    try:
+        gr.Info(i18n("处理数据"))
+    except:
+        pass
+    return i18n("处理数据"), {"value":dir,"__type__":"update"}
+
+def download_model_files(model):
+    model_found = False
+    index_found = False
+    if os.path.exists(f'./assets/weights/{model}.pth'): model_found = True
+    if os.path.exists(f'./logs/{model}'):
+        for file in os.listdir(f'./logs/{model}'):
+            if file.endswith('.index') and 'added' in file:
+                log_file = file
+                index_found = True
+    if model_found and index_found:
+        return [f'./assets/weights/{model}.pth', f'./logs/{model}/{log_file}'], "Done"
+    elif model_found and not index_found:
+        return f'./assets/weights/{model}.pth', "Could not find Index file."
+    elif index_found and not model_found:
+        return f'./logs/{model}/{log_file}', f'Make sure the Voice Name is correct. I could not find {model}.pth'
+    else:
+        return None, f'Could not find {model}.pth or corresponding Index file.'
+
+with gr.Blocks(title="KPOPEASYGUI 🔊",theme=gr.themes.Base(primary_hue="rose", secondary_hue="pink", neutral_hue="slate")) as app:
+    with gr.Row():
+        gr.HTML("<img  src='file/lp.gif' alt='image/gif'>")
+    with gr.Tabs():
+        with gr.TabItem(i18n("模型推理")):
+            with gr.Row():
+                sid0 = gr.Dropdown(label=i18n("推理音色"), choices=sorted(names), value=find_model())
+                refresh_button = gr.Button(i18n("刷新音色列表和索引路径"), variant="primary")
+                #clean_button = gr.Button(i18n("卸载音色省显存"), variant="primary")
+                spk_item = gr.Slider(
+                    minimum=0,
+                    maximum=2333,
+                    step=1,
+                    label=i18n("请选择说话人id"),
+                    value=0,
+                    visible=False,
+                    interactive=True,
+                )
+                #clean_button.click(
+                #    fn=clean, inputs=[], outputs=[sid0], api_name="infer_clean"
+                #)
+                vc_transform0 = gr.Number(
+                    label=i18n("变调(整数, 半音数量, 升八度12降八度-12)"), value=0
+                )
+                but0 = gr.Button(i18n("转换"), variant="primary")
+            with gr.Row():
+                with gr.Column():
+                    with gr.Row():
+                        dropbox = gr.File(label="Drop your audio here & hit the Reload button.")
+                    with gr.Row():
+                        record_button=gr.Audio(source="microphone", label="OR Record audio.", type="filepath")
+                    with gr.Row():
+                        input_audio0 = gr.Dropdown(
+                            label=i18n("输入待处理音频文件路径(默认是正确格式示例)"),
+                            value=find_audios(True),
+                            choices=find_audios()
+                        )
+                        record_button.change(fn=save_wav, inputs=[record_button], outputs=[input_audio0])
+                        dropbox.upload(fn=save_wav, inputs=[dropbox], outputs=[input_audio0])
+                with gr.Column():
+                    with gr.Accordion(label=i18n("自动检测index路径,下拉式选择(dropdown)"), open=False):
+                        file_index2 = gr.Dropdown(
+                            label=i18n("自动检测index路径,下拉式选择(dropdown)"),
+                            choices=get_indexes(),
+                            interactive=True,
+                            value=get_index()
+                        )
+                        index_rate1 = gr.Slider(
+                            minimum=0,
+                            maximum=1,
+                            label=i18n("检索特征占比"),
+                            value=0.66,
+                            interactive=True,
+                        )
+                    vc_output2 = gr.Audio(label=i18n("输出音频(右下角三个点,点了可以下载)"))
+                    with gr.Accordion(label=i18n("常规设置"), open=False):
+                        f0method0 = gr.Radio(
+                            label=i18n(
+                                "选择音高提取算法,输入歌声可用pm提速,harvest低音好但巨慢无比,crepe效果好但吃GPU,rmvpe效果最好且微吃GPU"
+                            ),
+                            choices=["pm", "harvest", "crepe", "rmvpe"]
+                            if config.dml == False
+                            else ["pm", "harvest", "rmvpe"],
+                            value="rmvpe",
+                            interactive=True,
+                        )
+                        filter_radius0 = gr.Slider(
+                            minimum=0,
+                            maximum=7,
+                            label=i18n(">=3则使用对harvest音高识别的结果使用中值滤波，数值为滤波半径，使用可以削弱哑音"),
+                            value=3,
+                            step=1,
+                            interactive=True,
+                        )
+                        resample_sr0 = gr.Slider(
+                            minimum=0,
+                            maximum=48000,
+                            label=i18n("后处理重采样至最终采样率，0为不进行重采样"),
+                            value=0,
+                            step=1,
+                            interactive=True,
+                            visible=False
+                        )
+                        rms_mix_rate0 = gr.Slider(
+                            minimum=0,
+                            maximum=1,
+                            label=i18n("输入源音量包络替换输出音量包络融合比例，越靠近1越使用输出包络"),
+                            value=0.21,
+                            interactive=True,
+                        )
+                        protect0 = gr.Slider(
+                            minimum=0,
+                            maximum=0.5,
+                            label=i18n(
+                                "保护清辅音和呼吸声，防止电音撕裂等artifact，拉满0.5不开启，调低加大保护力度但可能降低索引效果"
+                            ),
+                            value=0.33,
+                            step=0.01,
+                            interactive=True,
+                        )
+                    file_index1 = gr.Textbox(
+                        label=i18n("特征检索库文件路径,为空则使用下拉的选择结果"),
+                        value="",
+                        interactive=True,
+                        visible=False
+                    )
+                    refresh_button.click(
+                        fn=change_choices,
+                        inputs=[],
+                        outputs=[sid0, file_index2, input_audio0],
+                        api_name="infer_refresh",
+                    )
+                    # file_big_npy1 = gr.Textbox(
+                    #     label=i18n("特征文件路径"),
+                    #     value="E:\\codes\py39\\vits_vc_gpu_train\\logs\\mi-test-1key\\total_fea.npy",
+                    #     interactive=True,
+                    # )
+            with gr.Row():
+                f0_file = gr.File(label=i18n("F0曲线文件, 可选, 一行一个音高, 代替默认F0及升降调"), visible=False)
+            with gr.Row():
+                vc_output1 = gr.Textbox(label=i18n("输出信息"))
+                but0.click(
+                    vc.vc_single,  
+                    [
+                        spk_item,
+                        input_audio0,
+                        vc_transform0,
+                        f0_file,
+                        f0method0,
+                        file_index1,
+                        file_index2,
+                        # file_big_npy1,
+                        index_rate1,
+                        filter_radius0,
+                        resample_sr0,
+                        rms_mix_rate0,
+                        protect0,
+                    ],
+                    [vc_output1, vc_output2],
+                    api_name="infer_convert",
+                )
+            with gr.Row():
+                with gr.Accordion(open=False, label=i18n("批量转换, 输入待转换音频文件夹, 或上传多个音频文件, 在指定文件夹(默认opt)下输出转换的音频. ")):                
+                    with gr.Row():
+                        opt_input = gr.Textbox(label=i18n("指定输出文件夹"), value="opt")
+                        vc_transform1 = gr.Number(
+                            label=i18n("变调(整数, 半音数量, 升八度12降八度-12)"), value=0
+                        )
+                        f0method1 = gr.Radio(
+                            label=i18n(
+                                "选择音高提取算法,输入歌声可用pm提速,harvest低音好但巨慢无比,crepe效果好但吃GPU,rmvpe效果最好且微吃GPU"
+                            ),
+                            choices=["pm", "harvest", "crepe", "rmvpe"]
+                            if config.dml == False
+                            else ["pm", "harvest", "rmvpe"],
+                            value="pm",
+                            interactive=True,
+                        )
+                    with gr.Row():
+                        filter_radius1 = gr.Slider(
+                            minimum=0,
+                            maximum=7,
+                            label=i18n(">=3则使用对harvest音高识别的结果使用中值滤波，数值为滤波半径，使用可以削弱哑音"),
+                            value=3,
+                            step=1,
+                            interactive=True,
+                            visible=False
+                        )
+                    with gr.Row():
+                        file_index3 = gr.Textbox(
+                            label=i18n("特征检索库文件路径,为空则使用下拉的选择结果"),
+                            value="",
+                            interactive=True,
+                            visible=False
+                        )
+                        file_index4 = gr.Dropdown(
+                            label=i18n("自动检测index路径,下拉式选择(dropdown)"),
+                            choices=sorted(index_paths),
+                            interactive=True,
+                            visible=False
+                        )
+                        refresh_button.click(
+                            fn=lambda: change_choices()[1],
+                            inputs=[],
+                            outputs=file_index4,
+                            api_name="infer_refresh_batch",
+                        )
+                        # file_big_npy2 = gr.Textbox(
+                        #     label=i18n("特征文件路径"),
+                        #     value="E:\\codes\\py39\\vits_vc_gpu_train\\logs\\mi-test-1key\\total_fea.npy",
+                        #     interactive=True,
+                        # )
+                        index_rate2 = gr.Slider(
+                            minimum=0,
+                            maximum=1,
+                            label=i18n("检索特征占比"),
+                            value=1,
+                            interactive=True,
+                            visible=False
+                        )
+                    with gr.Row():
+                        resample_sr1 = gr.Slider(
+                            minimum=0,
+                            maximum=48000,
+                            label=i18n("后处理重采样至最终采样率，0为不进行重采样"),
+                            value=0,
+                            step=1,
+                            interactive=True,
+                            visible=False
+                        )
+                        rms_mix_rate1 = gr.Slider(
+                            minimum=0,
+                            maximum=1,
+                            label=i18n("输入源音量包络替换输出音量包络融合比例，越靠近1越使用输出包络"),
+                            value=0.21,
+                            interactive=True,
+                        )
+                        protect1 = gr.Slider(
+                            minimum=0,
+                            maximum=0.5,
+                            label=i18n(
+                                "保护清辅音和呼吸声，防止电音撕裂等artifact，拉满0.5不开启，调低加大保护力度但可能降低索引效果"
+                            ),
+                            value=0.33,
+                            step=0.01,
+                            interactive=True,
+                        )
+                    with gr.Row():
+                        dir_input = gr.Textbox(
+                            label=i18n("输入待处理音频文件夹路径(去文件管理器地址栏拷就行了)"),
+                            value="./audios",
+                        )
+                        inputs = gr.File(
+                            file_count="multiple", label=i18n("也可批量输入音频文件, 二选一, 优先读文件夹")
+                        )
+                    with gr.Row():
+                        format1 = gr.Radio(
+                            label=i18n("导出文件格式"),
+                            choices=["wav", "flac", "mp3", "m4a"],
+                            value="wav",
+                            interactive=True,
+                        )
+                        but1 = gr.Button(i18n("转换"), variant="primary")
+                        vc_output3 = gr.Textbox(label=i18n("输出信息"))
+                        but1.click(
+                            vc.vc_multi,
+                            [
+                                spk_item,
+                                dir_input,
+                                opt_input,
+                                inputs,
+                                vc_transform1,
+                                f0method1,
+                                file_index1,
+                                file_index2,
+                                # file_big_npy2,
+                                index_rate1,
+                                filter_radius1,
+                                resample_sr1,
+                                rms_mix_rate1,
+                                protect1,
+                                format1,
+                            ],
+                            [vc_output3],
+                            api_name="infer_convert_batch",
+                        )
+            sid0.change(
+                fn=vc.get_vc,
+                inputs=[sid0, protect0, protect1],
+                outputs=[spk_item, protect0, protect1, file_index2, file_index4],
+            )
+        with gr.TabItem("Download Model"):
+            with gr.Row():
+                gr.Markdown(
+                """
+                ⚠️ Google Drive Links, V1 models, and some leelo models will not work with this gradio ⚠️
+                """
+                )
+            with gr.Row():
+                url=gr.Textbox(label="Enter the URL to the Model:")
+            with gr.Row():
+                model = gr.Textbox(label="Name your model:")
+                download_button=gr.Button("Download")
+            with gr.Row():
+                status_bar=gr.Textbox(label="")
+                download_button.click(fn=download_from_url, inputs=[url, model], outputs=[status_bar])
+            with gr.Row():
+                gr.Markdown(
+                """
+                ❤️ Support Original Creator from this easyGUI ❤️ 
+                paypal.me/lesantillan
+                """
+                )
+        with gr.TabItem(i18n("训练")):
+            with gr.Row():
+                with gr.Column():
+                    exp_dir1 = gr.Textbox(label=i18n("输入实验名"), value="My-Voice")
+                    np7 = gr.Slider(
+                        minimum=0,
+                        maximum=config.n_cpu,
+                        step=1,
+                        label=i18n("提取音高和处理数据使用的CPU进程数"),
+                        value=int(np.ceil(config.n_cpu / 1.5)),
+                        interactive=True,
+                    )
+                    sr2 = gr.Radio(
+                        label=i18n("目标采样率"),
+                        choices=["40k", "48k"],
+                        value="40k",
+                        interactive=True,
+                        visible=False
+                    )
+                    if_f0_3 = gr.Radio(
+                        label=i18n("模型是否带音高指导(唱歌一定要, 语音可以不要)"),
+                        choices=[True, False],
+                        value=True,
+                        interactive=True,
+                        visible=False
+                    )
+                    version19 = gr.Radio(
+                        label=i18n("版本"),
+                        choices=["v1", "v2"],
+                        value="v2",
+                        interactive=True,
+                        visible=False,
+                    )
+                    trainset_dir4 = gr.Textbox(
+                        label=i18n("输入训练文件夹路径"), value='./dataset/'+datetime.datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
+                    )
+                    easy_uploader = gr.Files(label=i18n("也可批量输入音频文件, 二选一, 优先读文件夹"),file_types=['audio'])
+                    but1 = gr.Button(i18n("处理数据"), variant="primary")
+                    info1 = gr.Textbox(label=i18n("输出信息"), value="")
+                    easy_uploader.upload(fn=upload_to_dataset, inputs=[easy_uploader, trainset_dir4], outputs=[info1, trainset_dir4])
+                    gpus6 = gr.Textbox(
+                        label=i18n("以-分隔输入使用的卡号, 例如   0-1-2   使用卡0和卡1和卡2"),
+                        value=gpus,
+                        interactive=True,
+                        visible=F0GPUVisible,
+                    )
+                    gpu_info9 = gr.Textbox(
+                        label=i18n("显卡信息"), value=gpu_info, visible=F0GPUVisible
+                    )
+                    spk_id5 = gr.Slider(
+                        minimum=0,
+                        maximum=4,
+                        step=1,
+                        label=i18n("请指定说话人id"),
+                        value=0,
+                        interactive=True,
+                        visible=False
+                    )
+                    but1.click(
+                        preprocess_dataset,
+                        [trainset_dir4, exp_dir1, sr2, np7],
+                        [info1],
+                        api_name="train_preprocess",
+                    ) 
+                with gr.Column():
+                    f0method8 = gr.Radio(
+                        label=i18n(
+                            "选择音高提取算法:输入歌声可用pm提速,高质量语音但CPU差可用dio提速,harvest质量更好但慢,rmvpe效果最好且微吃CPU/GPU"
+                        ),
+                        choices=["pm", "harvest", "dio", "rmvpe", "rmvpe_gpu"],
+                        value="rmvpe_gpu",
+                        interactive=True,
+                    )
+                    gpus_rmvpe = gr.Textbox(
+                        label=i18n(
+                            "rmvpe卡号配置：以-分隔输入使用的不同进程卡号,例如0-0-1使用在卡0上跑2个进程并在卡1上跑1个进程"
+                        ),
+                        value="%s-%s" % (gpus, gpus),
+                        interactive=True,
+                        visible=F0GPUVisible,
+                    )
+                    but2 = gr.Button(i18n("特征提取"), variant="primary")
+                    info2 = gr.Textbox(label=i18n("输出信息"), value="", max_lines=8)
+                    f0method8.change(
+                        fn=change_f0_method,
+                        inputs=[f0method8],
+                        outputs=[gpus_rmvpe],
+                    )
+                    but2.click(
+                        extract_f0_feature,
+                        [
+                            gpus6,
+                            np7,
+                            f0method8,
+                            if_f0_3,
+                            exp_dir1,
+                            version19,
+                            gpus_rmvpe,
+                        ],
+                        [info2],
+                        api_name="train_extract_f0_feature",
+                    )
+                with gr.Column():
+                    total_epoch11 = gr.Slider(
+                        minimum=2,
+                        maximum=1000,
+                        step=1,
+                        label=i18n("总训练轮数total_epoch"),
+                        value=150,
+                        interactive=True,
+                    )
+                    gpus16 = gr.Textbox(
+                            label=i18n("以-分隔输入使用的卡号, 例如   0-1-2   使用卡0和卡1和卡2"),
+                            value="0",
+                            interactive=True,
+                            visible=True
+                        )
+                    but3 = gr.Button(i18n("训练模型"), variant="primary")
+                    but4 = gr.Button(i18n("训练特征索引"), variant="primary")
+                    info3 = gr.Textbox(label=i18n("输出信息"), value="", max_lines=10)
+                    with gr.Accordion(label=i18n("常规设置"), open=False):
+                        save_epoch10 = gr.Slider(
+                            minimum=1,
+                            maximum=50,
+                            step=1,
+                            label=i18n("保存频率save_every_epoch"),
+                            value=25,
+                            interactive=True,
+                        )
+                        batch_size12 = gr.Slider(
+                            minimum=1,
+                            maximum=40,
+                            step=1,
+                            label=i18n("每张显卡的batch_size"),
+                            value=default_batch_size,
+                            interactive=True,
+                        )
+                        if_save_latest13 = gr.Radio(
+                            label=i18n("是否仅保存最新的ckpt文件以节省硬盘空间"),
+                            choices=[i18n("是"), i18n("否")],
+                            value=i18n("是"),
+                            interactive=True,
+                            visible=False
+                        )
+                        if_cache_gpu17 = gr.Radio(
+                            label=i18n(
+                                "是否缓存所有训练集至显存. 10min以下小数据可缓存以加速训练, 大数据缓存会炸显存也加不了多少速"
+                            ),
+                            choices=[i18n("是"), i18n("否")],
+                            value=i18n("否"),
+                            interactive=True,
+                        )
+                        if_save_every_weights18 = gr.Radio(
+                            label=i18n("是否在每次保存时间点将最终小模型保存至weights文件夹"),
+                            choices=[i18n("是"), i18n("否")],
+                            value=i18n("是"),
+                            interactive=True,
+                        )
+                    with gr.Row():
+                        download_model = gr.Button('5.Download Model')
+                    with gr.Row():
+                        model_files = gr.Files(label='Your Model and Index file can be downloaded here:')
+                        download_model.click(fn=download_model_files, inputs=[exp_dir1], outputs=[model_files, info3])
+                    with gr.Row():
+                        pretrained_G14 = gr.Textbox(
+                            label=i18n("加载预训练底模G路径"),
+                            value="assets/pretrained_v2/f0G40k.pth",
+                            interactive=True,
+                            visible=False
+                        )
+                        pretrained_D15 = gr.Textbox(
+                            label=i18n("加载预训练底模D路径"),
+                            value="assets/pretrained_v2/f0D40k.pth",
+                            interactive=True,
+                            visible=False
+                        )
+                        sr2.change(
+                            change_sr2,
+                            [sr2, if_f0_3, version19],
+                            [pretrained_G14, pretrained_D15],
+                        )
+                        version19.change(
+                            change_version19,
+                            [sr2, if_f0_3, version19],
+                            [pretrained_G14, pretrained_D15, sr2],
+                        )
+                        if_f0_3.change(
+                            change_f0,
+                            [if_f0_3, sr2, version19],
+                            [f0method8, pretrained_G14, pretrained_D15],
+                        )
+                    with gr.Row():
+                        but5 = gr.Button(i18n("一键训练"), variant="primary", visible=False)
+                        but3.click(
+                            click_train,
+                            [
+                                exp_dir1,
+                                sr2,
+                                if_f0_3,
+                                spk_id5,
+                                save_epoch10,
+                                total_epoch11,
+                                batch_size12,
+                                if_save_latest13,
+                                pretrained_G14,
+                                pretrained_D15,
+                                gpus16,
+                                if_cache_gpu17,
+                                if_save_every_weights18,
+                                version19,
+                            ],
+                            info3,
+                            api_name="train_start",
+                        )
+                        but4.click(train_index, [exp_dir1, version19], info3)
+                        but5.click(
+                            train1key,
+                            [
+                                exp_dir1,
+                                sr2,
+                                if_f0_3,
+                                trainset_dir4,
+                                spk_id5,
+                                np7,
+                                f0method8,
+                                save_epoch10,
+                                total_epoch11,
+                                batch_size12,
+                                if_save_latest13,
+                                pretrained_G14,
+                                pretrained_D15,
+                                gpus16,
+                                if_cache_gpu17,
+                                if_save_every_weights18,
+                                version19,
+                                gpus_rmvpe,
+                            ],
+                            info3,
+                            api_name="train_start_all",
+                        )
+
+    if config.iscolab:
+        app.queue(concurrency_count=511, max_size=1022).launch(share=True),
+        favicon_path="file/Logo_of_TWICE.svg.png"
+    else:
+        app.queue(concurrency_count=511, max_size=1022).launch(
+            server_name="0.0.0.0",
+            favicon_path="file/Logo_of_TWICE.svg.png",
+            inbrowser=not config.noautoopen,
+            server_port=config.listen_port,
+            quiet=True,
+        )

docker-compose.yml

@@ -0,0 +1,13 @@
+version: "3.8"
+services:
+  rvc:
+    build:
+      context: .
+      dockerfile: Dockerfile
+    container_name: rvc
+    volumes:
+      - ./weights:/app/assets/weights
+      - ./opt:/app/opt
+      # - ./dataset:/app/dataset # you can use this folder in order to provide your dataset for model training
+    ports:
+      - 7865:7865

download_files.py

@@ -0,0 +1,19 @@
+import subprocess, os
+assets_folder = "./assets/"
+if not os.path.exists(assets_folder):
+    os.makedirs(assets_folder)
+files = {
+    "rmvpe/rmvpe.pt":"https://huggingface.co/Rejekts/project/resolve/main/rmvpe.pt",
+    "hubert/hubert_base.pt":"https://huggingface.co/Rejekts/project/resolve/main/hubert_base.pt",
+    "pretrained_v2/D40k.pth":"https://huggingface.co/Rejekts/project/resolve/main/D40k.pth",
+    "pretrained_v2/G40k.pth":"https://huggingface.co/Rejekts/project/resolve/main/G40k.pth",
+    "pretrained_v2/f0D40k.pth":"https://huggingface.co/Rejekts/project/resolve/main/f0D40k.pth",
+    "pretrained_v2/f0G40k.pth":"https://huggingface.co/Rejekts/project/resolve/main/f0G40k.pth"
+}
+for file, link in files.items():
+    file_path = os.path.join(assets_folder, file)
+    if not os.path.exists(file_path):
+        try:
+            subprocess.run(['wget', link, '-O', file_path], check=True)
+        except subprocess.CalledProcessError as e:
+            print(f"Error downloading {file}: {e}")

environment_dml.yaml

@@ -0,0 +1,186 @@
+name: pydml
+channels:
+  - pytorch
+  - https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
+  - https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main/
+  - https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free/
+  - https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/conda-forge/
+  - defaults
+  - https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/fastai/
+  - https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/pytorch/
+  - https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/bioconda/
+dependencies:
+  - abseil-cpp=20211102.0=hd77b12b_0
+  - absl-py=1.3.0=py310haa95532_0
+  - aiohttp=3.8.3=py310h2bbff1b_0
+  - aiosignal=1.2.0=pyhd3eb1b0_0
+  - async-timeout=4.0.2=py310haa95532_0
+  - attrs=22.1.0=py310haa95532_0
+  - blas=1.0=mkl
+  - blinker=1.4=py310haa95532_0
+  - bottleneck=1.3.5=py310h9128911_0
+  - brotli=1.0.9=h2bbff1b_7
+  - brotli-bin=1.0.9=h2bbff1b_7
+  - brotlipy=0.7.0=py310h2bbff1b_1002
+  - bzip2=1.0.8=he774522_0
+  - c-ares=1.19.0=h2bbff1b_0
+  - ca-certificates=2023.05.30=haa95532_0
+  - cachetools=4.2.2=pyhd3eb1b0_0
+  - certifi=2023.5.7=py310haa95532_0
+  - cffi=1.15.1=py310h2bbff1b_3
+  - charset-normalizer=2.0.4=pyhd3eb1b0_0
+  - click=8.0.4=py310haa95532_0
+  - colorama=0.4.6=py310haa95532_0
+  - contourpy=1.0.5=py310h59b6b97_0
+  - cryptography=39.0.1=py310h21b164f_0
+  - cycler=0.11.0=pyhd3eb1b0_0
+  - fonttools=4.25.0=pyhd3eb1b0_0
+  - freetype=2.12.1=ha860e81_0
+  - frozenlist=1.3.3=py310h2bbff1b_0
+  - giflib=5.2.1=h8cc25b3_3
+  - glib=2.69.1=h5dc1a3c_2
+  - google-auth=2.6.0=pyhd3eb1b0_0
+  - google-auth-oauthlib=0.4.4=pyhd3eb1b0_0
+  - grpc-cpp=1.48.2=hf108199_0
+  - grpcio=1.48.2=py310hf108199_0
+  - gst-plugins-base=1.18.5=h9e645db_0
+  - gstreamer=1.18.5=hd78058f_0
+  - icu=58.2=ha925a31_3
+  - idna=3.4=py310haa95532_0
+  - intel-openmp=2023.1.0=h59b6b97_46319
+  - jpeg=9e=h2bbff1b_1
+  - kiwisolver=1.4.4=py310hd77b12b_0
+  - krb5=1.19.4=h5b6d351_0
+  - lerc=3.0=hd77b12b_0
+  - libbrotlicommon=1.0.9=h2bbff1b_7
+  - libbrotlidec=1.0.9=h2bbff1b_7
+  - libbrotlienc=1.0.9=h2bbff1b_7
+  - libclang=14.0.6=default_hb5a9fac_1
+  - libclang13=14.0.6=default_h8e68704_1
+  - libdeflate=1.17=h2bbff1b_0
+  - libffi=3.4.4=hd77b12b_0
+  - libiconv=1.16=h2bbff1b_2
+  - libogg=1.3.5=h2bbff1b_1
+  - libpng=1.6.39=h8cc25b3_0
+  - libprotobuf=3.20.3=h23ce68f_0
+  - libtiff=4.5.0=h6c2663c_2
+  - libuv=1.44.2=h2bbff1b_0
+  - libvorbis=1.3.7=he774522_0
+  - libwebp=1.2.4=hbc33d0d_1
+  - libwebp-base=1.2.4=h2bbff1b_1
+  - libxml2=2.10.3=h0ad7f3c_0
+  - libxslt=1.1.37=h2bbff1b_0
+  - lz4-c=1.9.4=h2bbff1b_0
+  - markdown=3.4.1=py310haa95532_0
+  - markupsafe=2.1.1=py310h2bbff1b_0
+  - matplotlib=3.7.1=py310haa95532_1
+  - matplotlib-base=3.7.1=py310h4ed8f06_1
+  - mkl=2023.1.0=h8bd8f75_46356
+  - mkl-service=2.4.0=py310h2bbff1b_1
+  - mkl_fft=1.3.6=py310h4ed8f06_1
+  - mkl_random=1.2.2=py310h4ed8f06_1
+  - multidict=6.0.2=py310h2bbff1b_0
+  - munkres=1.1.4=py_0
+  - numexpr=2.8.4=py310h2cd9be0_1
+  - numpy=1.24.3=py310h055cbcc_1
+  - numpy-base=1.24.3=py310h65a83cf_1
+  - oauthlib=3.2.2=py310haa95532_0
+  - openssl=1.1.1t=h2bbff1b_0
+  - packaging=23.0=py310haa95532_0
+  - pandas=1.5.3=py310h4ed8f06_0
+  - pcre=8.45=hd77b12b_0
+  - pillow=9.4.0=py310hd77b12b_0
+  - pip=23.0.1=py310haa95532_0
+  - ply=3.11=py310haa95532_0
+  - protobuf=3.20.3=py310hd77b12b_0
+  - pyasn1=0.4.8=pyhd3eb1b0_0
+  - pyasn1-modules=0.2.8=py_0
+  - pycparser=2.21=pyhd3eb1b0_0
+  - pyjwt=2.4.0=py310haa95532_0
+  - pyopenssl=23.0.0=py310haa95532_0
+  - pyparsing=3.0.9=py310haa95532_0
+  - pyqt=5.15.7=py310hd77b12b_0
+  - pyqt5-sip=12.11.0=py310hd77b12b_0
+  - pysocks=1.7.1=py310haa95532_0
+  - python=3.10.11=h966fe2a_2
+  - python-dateutil=2.8.2=pyhd3eb1b0_0
+  - pytorch-mutex=1.0=cpu
+  - pytz=2022.7=py310haa95532_0
+  - pyyaml=6.0=py310h2bbff1b_1
+  - qt-main=5.15.2=he8e5bd7_8
+  - qt-webengine=5.15.9=hb9a9bb5_5
+  - qtwebkit=5.212=h2bbfb41_5
+  - re2=2022.04.01=hd77b12b_0
+  - requests=2.29.0=py310haa95532_0
+  - requests-oauthlib=1.3.0=py_0
+  - rsa=4.7.2=pyhd3eb1b0_1
+  - setuptools=67.8.0=py310haa95532_0
+  - sip=6.6.2=py310hd77b12b_0
+  - six=1.16.0=pyhd3eb1b0_1
+  - sqlite=3.41.2=h2bbff1b_0
+  - tbb=2021.8.0=h59b6b97_0
+  - tensorboard=2.10.0=py310haa95532_0
+  - tensorboard-data-server=0.6.1=py310haa95532_0
+  - tensorboard-plugin-wit=1.8.1=py310haa95532_0
+  - tk=8.6.12=h2bbff1b_0
+  - toml=0.10.2=pyhd3eb1b0_0
+  - tornado=6.2=py310h2bbff1b_0
+  - tqdm=4.65.0=py310h9909e9c_0
+  - typing_extensions=4.5.0=py310haa95532_0
+  - tzdata=2023c=h04d1e81_0
+  - urllib3=1.26.16=py310haa95532_0
+  - vc=14.2=h21ff451_1
+  - vs2015_runtime=14.27.29016=h5e58377_2
+  - werkzeug=2.2.3=py310haa95532_0
+  - wheel=0.38.4=py310haa95532_0
+  - win_inet_pton=1.1.0=py310haa95532_0
+  - xz=5.4.2=h8cc25b3_0
+  - yaml=0.2.5=he774522_0
+  - yarl=1.8.1=py310h2bbff1b_0
+  - zlib=1.2.13=h8cc25b3_0
+  - zstd=1.5.5=hd43e919_0
+  - pip:
+      - antlr4-python3-runtime==4.8
+      - appdirs==1.4.4
+      - audioread==3.0.0
+      - bitarray==2.7.4
+      - cython==0.29.35
+      - decorator==5.1.1
+      - fairseq==0.12.2
+      - faiss-cpu==1.7.4
+      - filelock==3.12.0
+      - hydra-core==1.0.7
+      - jinja2==3.1.2
+      - joblib==1.2.0
+      - lazy-loader==0.2
+      - librosa==0.10.0.post2
+      - llvmlite==0.40.0
+      - lxml==4.9.2
+      - mpmath==1.3.0
+      - msgpack==1.0.5
+      - networkx==3.1
+      - noisereduce==2.0.1
+      - numba==0.57.0
+      - omegaconf==2.0.6
+      - opencv-python==4.7.0.72
+      - pooch==1.6.0
+      - portalocker==2.7.0
+      - pysimplegui==4.60.5
+      - pywin32==306
+      - pyworld==0.3.3
+      - regex==2023.5.5
+      - sacrebleu==2.3.1
+      - scikit-learn==1.2.2
+      - scipy==1.10.1
+      - sounddevice==0.4.6
+      - soundfile==0.12.1
+      - soxr==0.3.5
+      - sympy==1.12
+      - tabulate==0.9.0
+      - threadpoolctl==3.1.0
+      - torch==2.0.0
+      - torch-directml==0.2.0.dev230426
+      - torchaudio==2.0.1
+      - torchvision==0.15.1
+      - wget==3.2
+prefix: D:\ProgramData\anaconda3_\envs\pydml

go-realtime-gui-dml.bat

@@ -0,0 +1,2 @@
+runtime\python.exe gui_v1.py --pycmd runtime\python.exe --dml
+pause

go-realtime-gui.bat

@@ -0,0 +1,2 @@
+runtime\python.exe gui_v1.py
+pause

go-web-dml.bat

@@ -0,0 +1,2 @@
+runtime\python.exe infer-web.py --pycmd runtime\python.exe --port 7897 --dml
+pause

go-web.bat

@@ -0,0 +1,2 @@
+runtime\python.exe infer-web.py --pycmd runtime\python.exe --port 7897
+pause

gui_v1.py

@@ -0,0 +1,708 @@
+import os
+import logging
+import sys
+from dotenv import load_dotenv
+
+load_dotenv()
+
+os.environ["OMP_NUM_THREADS"] = "4"
+if sys.platform == "darwin":
+    os.environ["PYTORCH_ENABLE_MPS_FALLBACK"] = "1"
+
+now_dir = os.getcwd()
+sys.path.append(now_dir)
+import multiprocessing
+
+logger = logging.getLogger(__name__)
+
+
+class Harvest(multiprocessing.Process):
+    def __init__(self, inp_q, opt_q):
+        multiprocessing.Process.__init__(self)
+        self.inp_q = inp_q
+        self.opt_q = opt_q
+
+    def run(self):
+        import numpy as np
+        import pyworld
+
+        while 1:
+            idx, x, res_f0, n_cpu, ts = self.inp_q.get()
+            f0, t = pyworld.harvest(
+                x.astype(np.double),
+                fs=16000,
+                f0_ceil=1100,
+                f0_floor=50,
+                frame_period=10,
+            )
+            res_f0[idx] = f0
+            if len(res_f0.keys()) >= n_cpu:
+                self.opt_q.put(ts)
+
+
+if __name__ == "__main__":
+    import json
+    import multiprocessing
+    import re
+    import threading
+    import time
+    import traceback
+    from multiprocessing import Queue, cpu_count
+    from queue import Empty
+
+    import librosa
+    from tools.torchgate import TorchGate
+    import numpy as np
+    import PySimpleGUI as sg
+    import sounddevice as sd
+    import torch
+    import torch.nn.functional as F
+    import torchaudio.transforms as tat
+
+    import tools.rvc_for_realtime as rvc_for_realtime
+    from i18n.i18n import I18nAuto
+
+    i18n = I18nAuto()
+    device = rvc_for_realtime.config.device
+    # device = torch.device(
+    #     "cuda"
+    #     if torch.cuda.is_available()
+    #     else ("mps" if torch.backends.mps.is_available() else "cpu")
+    # )
+    current_dir = os.getcwd()
+    inp_q = Queue()
+    opt_q = Queue()
+    n_cpu = min(cpu_count(), 8)
+    for _ in range(n_cpu):
+        Harvest(inp_q, opt_q).start()
+
+    class GUIConfig:
+        def __init__(self) -> None:
+            self.pth_path: str = ""
+            self.index_path: str = ""
+            self.pitch: int = 0
+            self.samplerate: int = 40000
+            self.block_time: float = 1.0  # s
+            self.buffer_num: int = 1
+            self.threhold: int = -60
+            self.crossfade_time: float = 0.04
+            self.extra_time: float = 2.0
+            self.I_noise_reduce = False
+            self.O_noise_reduce = False
+            self.rms_mix_rate = 0.0
+            self.index_rate = 0.3
+            self.n_cpu = min(n_cpu, 6)
+            self.f0method = "harvest"
+            self.sg_input_device = ""
+            self.sg_output_device = ""
+
+    class GUI:
+        def __init__(self) -> None:
+            self.config = GUIConfig()
+            self.flag_vc = False
+
+            self.launcher()
+
+        def load(self):
+            input_devices, output_devices, _, _ = self.get_devices()
+            try:
+                with open("configs/config.json", "r") as j:
+                    data = json.load(j)
+                    data["pm"] = data["f0method"] == "pm"
+                    data["harvest"] = data["f0method"] == "harvest"
+                    data["crepe"] = data["f0method"] == "crepe"
+                    data["rmvpe"] = data["f0method"] == "rmvpe"
+            except:
+                with open("configs/config.json", "w") as j:
+                    data = {
+                        "pth_path": " ",
+                        "index_path": " ",
+                        "sg_input_device": input_devices[sd.default.device[0]],
+                        "sg_output_device": output_devices[sd.default.device[1]],
+                        "threhold": "-60",
+                        "pitch": "0",
+                        "index_rate": "0",
+                        "rms_mix_rate": "0",
+                        "block_time": "0.25",
+                        "crossfade_length": "0.04",
+                        "extra_time": "2",
+                        "f0method": "rmvpe",
+                    }
+                    data["pm"] = data["f0method"] == "pm"
+                    data["harvest"] = data["f0method"] == "harvest"
+                    data["crepe"] = data["f0method"] == "crepe"
+                    data["rmvpe"] = data["f0method"] == "rmvpe"
+            return data
+
+        def launcher(self):
+            data = self.load()
+            sg.theme("LightBlue3")
+            input_devices, output_devices, _, _ = self.get_devices()
+            layout = [
+                [
+                    sg.Frame(
+                        title=i18n("加载模型"),
+                        layout=[
+                            [
+                                sg.Input(
+                                    default_text=data.get("pth_path", ""),
+                                    key="pth_path",
+                                ),
+                                sg.FileBrowse(
+                                    i18n("选择.pth文件"),
+                                    initial_folder=os.path.join(
+                                        os.getcwd(), "assets/weights"
+                                    ),
+                                    file_types=((". pth"),),
+                                ),
+                            ],
+                            [
+                                sg.Input(
+                                    default_text=data.get("index_path", ""),
+                                    key="index_path",
+                                ),
+                                sg.FileBrowse(
+                                    i18n("选择.index文件"),
+                                    initial_folder=os.path.join(os.getcwd(), "logs"),
+                                    file_types=((". index"),),
+                                ),
+                            ],
+                        ],
+                    )
+                ],
+                [
+                    sg.Frame(
+                        layout=[
+                            [
+                                sg.Text(i18n("输入设备")),
+                                sg.Combo(
+                                    input_devices,
+                                    key="sg_input_device",
+                                    default_value=data.get("sg_input_device", ""),
+                                ),
+                            ],
+                            [
+                                sg.Text(i18n("输出设备")),
+                                sg.Combo(
+                                    output_devices,
+                                    key="sg_output_device",
+                                    default_value=data.get("sg_output_device", ""),
+                                ),
+                            ],
+                            [sg.Button(i18n("重载设备列表"), key="reload_devices")],
+                        ],
+                        title=i18n("音频设备(请使用同种类驱动)"),
+                    )
+                ],
+                [
+                    sg.Frame(
+                        layout=[
+                            [
+                                sg.Text(i18n("响应阈值")),
+                                sg.Slider(
+                                    range=(-60, 0),
+                                    key="threhold",
+                                    resolution=1,
+                                    orientation="h",
+                                    default_value=data.get("threhold", "-60"),
+                                    enable_events=True,
+                                ),
+                            ],
+                            [
+                                sg.Text(i18n("音调设置")),
+                                sg.Slider(
+                                    range=(-24, 24),
+                                    key="pitch",
+                                    resolution=1,
+                                    orientation="h",
+                                    default_value=data.get("pitch", "0"),
+                                    enable_events=True,
+                                ),
+                            ],
+                            [
+                                sg.Text(i18n("Index Rate")),
+                                sg.Slider(
+                                    range=(0.0, 1.0),
+                                    key="index_rate",
+                                    resolution=0.01,
+                                    orientation="h",
+                                    default_value=data.get("index_rate", "0"),
+                                    enable_events=True,
+                                ),
+                            ],
+                            [
+                                sg.Text(i18n("响度因子")),
+                                sg.Slider(
+                                    range=(0.0, 1.0),
+                                    key="rms_mix_rate",
+                                    resolution=0.01,
+                                    orientation="h",
+                                    default_value=data.get("rms_mix_rate", "0"),
+                                    enable_events=True,
+                                ),
+                            ],
+                            [
+                                sg.Text(i18n("音高算法")),
+                                sg.Radio(
+                                    "pm",
+                                    "f0method",
+                                    key="pm",
+                                    default=data.get("pm", "") == True,
+                                    enable_events=True,
+                                ),
+                                sg.Radio(
+                                    "harvest",
+                                    "f0method",
+                                    key="harvest",
+                                    default=data.get("harvest", "") == True,
+                                    enable_events=True,
+                                ),
+                                sg.Radio(
+                                    "crepe",
+                                    "f0method",
+                                    key="crepe",
+                                    default=data.get("crepe", "") == True,
+                                    enable_events=True,
+                                ),
+                                sg.Radio(
+                                    "rmvpe",
+                                    "f0method",
+                                    key="rmvpe",
+                                    default=data.get("rmvpe", "") == True,
+                                    enable_events=True,
+                                ),
+                            ],
+                        ],
+                        title=i18n("常规设置"),
+                    ),
+                    sg.Frame(
+                        layout=[
+                            [
+                                sg.Text(i18n("采样长度")),
+                                sg.Slider(
+                                    range=(0.05, 2.4),
+                                    key="block_time",
+                                    resolution=0.01,
+                                    orientation="h",
+                                    default_value=data.get("block_time", "0.25"),
+                                    enable_events=True,
+                                ),
+                            ],
+                            [
+                                sg.Text(i18n("harvest进程数")),
+                                sg.Slider(
+                                    range=(1, n_cpu),
+                                    key="n_cpu",
+                                    resolution=1,
+                                    orientation="h",
+                                    default_value=data.get(
+                                        "n_cpu", min(self.config.n_cpu, n_cpu)
+                                    ),
+                                    enable_events=True,
+                                ),
+                            ],
+                            [
+                                sg.Text(i18n("淡入淡出长度")),
+                                sg.Slider(
+                                    range=(0.01, 0.15),
+                                    key="crossfade_length",
+                                    resolution=0.01,
+                                    orientation="h",
+                                    default_value=data.get("crossfade_length", "0.04"),
+                                    enable_events=True,
+                                ),
+                            ],
+                            [
+                                sg.Text(i18n("额外推理时长")),
+                                sg.Slider(
+                                    range=(0.05, 5.00),
+                                    key="extra_time",
+                                    resolution=0.01,
+                                    orientation="h",
+                                    default_value=data.get("extra_time", "2.0"),
+                                    enable_events=True,
+                                ),
+                            ],
+                            [
+                                sg.Checkbox(
+                                    i18n("输入降噪"),
+                                    key="I_noise_reduce",
+                                    enable_events=True,
+                                ),
+                                sg.Checkbox(
+                                    i18n("输出降噪"),
+                                    key="O_noise_reduce",
+                                    enable_events=True,
+                                ),
+                            ],
+                        ],
+                        title=i18n("性能设置"),
+                    ),
+                ],
+                [
+                    sg.Button(i18n("开始音频转换"), key="start_vc"),
+                    sg.Button(i18n("停止音频转换"), key="stop_vc"),
+                    sg.Text(i18n("推理时间(ms):")),
+                    sg.Text("0", key="infer_time"),
+                ],
+            ]
+            self.window = sg.Window("RVC - GUI", layout=layout, finalize=True)
+            self.event_handler()
+
+        def event_handler(self):
+            while True:
+                event, values = self.window.read()
+                if event == sg.WINDOW_CLOSED:
+                    self.flag_vc = False
+                    exit()
+                if event == "reload_devices":
+                    prev_input = self.window["sg_input_device"].get()
+                    prev_output = self.window["sg_output_device"].get()
+                    input_devices, output_devices, _, _ = self.get_devices(update=True)
+                    if prev_input not in input_devices:
+                        self.config.sg_input_device = input_devices[0]
+                    else:
+                        self.config.sg_input_device = prev_input
+                    self.window["sg_input_device"].Update(values=input_devices)
+                    self.window["sg_input_device"].Update(
+                        value=self.config.sg_input_device
+                    )
+                    if prev_output not in output_devices:
+                        self.config.sg_output_device = output_devices[0]
+                    else:
+                        self.config.sg_output_device = prev_output
+                    self.window["sg_output_device"].Update(values=output_devices)
+                    self.window["sg_output_device"].Update(
+                        value=self.config.sg_output_device
+                    )
+                if event == "start_vc" and self.flag_vc == False:
+                    if self.set_values(values) == True:
+                        logger.info("Use CUDA: %s", torch.cuda.is_available())
+                        self.start_vc()
+                        settings = {
+                            "pth_path": values["pth_path"],
+                            "index_path": values["index_path"],
+                            "sg_input_device": values["sg_input_device"],
+                            "sg_output_device": values["sg_output_device"],
+                            "threhold": values["threhold"],
+                            "pitch": values["pitch"],
+                            "rms_mix_rate": values["rms_mix_rate"],
+                            "index_rate": values["index_rate"],
+                            "block_time": values["block_time"],
+                            "crossfade_length": values["crossfade_length"],
+                            "extra_time": values["extra_time"],
+                            "n_cpu": values["n_cpu"],
+                            "f0method": ["pm", "harvest", "crepe", "rmvpe"][
+                                [
+                                    values["pm"],
+                                    values["harvest"],
+                                    values["crepe"],
+                                    values["rmvpe"],
+                                ].index(True)
+                            ],
+                        }
+                        with open("configs/config.json", "w") as j:
+                            json.dump(settings, j)
+                if event == "stop_vc" and self.flag_vc == True:
+                    self.flag_vc = False
+
+                # Parameter hot update
+                if event == "threhold":
+                    self.config.threhold = values["threhold"]
+                elif event == "pitch":
+                    self.config.pitch = values["pitch"]
+                    if hasattr(self, "rvc"):
+                        self.rvc.change_key(values["pitch"])
+                elif event == "index_rate":
+                    self.config.index_rate = values["index_rate"]
+                    if hasattr(self, "rvc"):
+                        self.rvc.change_index_rate(values["index_rate"])
+                elif event == "rms_mix_rate":
+                    self.config.rms_mix_rate = values["rms_mix_rate"]
+                elif event in ["pm", "harvest", "crepe", "rmvpe"]:
+                    self.config.f0method = event
+                elif event == "I_noise_reduce":
+                    self.config.I_noise_reduce = values["I_noise_reduce"]
+                elif event == "O_noise_reduce":
+                    self.config.O_noise_reduce = values["O_noise_reduce"]
+                elif event != "start_vc" and self.flag_vc == True:
+                    # Other parameters do not support hot update
+                    self.flag_vc = False
+
+        def set_values(self, values):
+            if len(values["pth_path"].strip()) == 0:
+                sg.popup(i18n("请选择pth文件"))
+                return False
+            if len(values["index_path"].strip()) == 0:
+                sg.popup(i18n("请选择index文件"))
+                return False
+            pattern = re.compile("[^\x00-\x7F]+")
+            if pattern.findall(values["pth_path"]):
+                sg.popup(i18n("pth文件路径不可包含中文"))
+                return False
+            if pattern.findall(values["index_path"]):
+                sg.popup(i18n("index文件路径不可包含中文"))
+                return False
+            self.set_devices(values["sg_input_device"], values["sg_output_device"])
+            self.config.pth_path = values["pth_path"]
+            self.config.index_path = values["index_path"]
+            self.config.threhold = values["threhold"]
+            self.config.pitch = values["pitch"]
+            self.config.block_time = values["block_time"]
+            self.config.crossfade_time = values["crossfade_length"]
+            self.config.extra_time = values["extra_time"]
+            self.config.I_noise_reduce = values["I_noise_reduce"]
+            self.config.O_noise_reduce = values["O_noise_reduce"]
+            self.config.rms_mix_rate = values["rms_mix_rate"]
+            self.config.index_rate = values["index_rate"]
+            self.config.n_cpu = values["n_cpu"]
+            self.config.f0method = ["pm", "harvest", "crepe", "rmvpe"][
+                [
+                    values["pm"],
+                    values["harvest"],
+                    values["crepe"],
+                    values["rmvpe"],
+                ].index(True)
+            ]
+            return True
+
+        def start_vc(self):
+            torch.cuda.empty_cache()
+            self.flag_vc = True
+            self.rvc = rvc_for_realtime.RVC(
+                self.config.pitch,
+                self.config.pth_path,
+                self.config.index_path,
+                self.config.index_rate,
+                self.config.n_cpu,
+                inp_q,
+                opt_q,
+                device,
+                self.rvc if hasattr(self, "rvc") else None
+            )
+            self.config.samplerate = self.rvc.tgt_sr
+            self.zc = self.rvc.tgt_sr // 100
+            self.block_frame = int(np.round(self.config.block_time * self.config.samplerate / self.zc)) * self.zc
+            self.block_frame_16k = 160 * self.block_frame // self.zc
+            self.crossfade_frame = int(np.round(self.config.crossfade_time * self.config.samplerate / self.zc)) * self.zc
+            self.sola_search_frame = self.zc
+            self.extra_frame = int(np.round(self.config.extra_time * self.config.samplerate / self.zc)) * self.zc
+            self.input_wav: torch.Tensor = torch.zeros(
+                self.extra_frame
+                + self.crossfade_frame
+                + self.sola_search_frame
+                + self.block_frame,
+                device=device,
+                dtype=torch.float32,
+            )
+            self.input_wav_res: torch.Tensor= torch.zeros(160 * self.input_wav.shape[0] // self.zc, device=device,dtype=torch.float32)
+            self.pitch: np.ndarray = np.zeros(
+                self.input_wav.shape[0] // self.zc,
+                dtype="int32",
+            )
+            self.pitchf: np.ndarray = np.zeros(
+                self.input_wav.shape[0] // self.zc,
+                dtype="float64",
+            )
+            self.sola_buffer: torch.Tensor = torch.zeros(
+                self.crossfade_frame, device=device, dtype=torch.float32
+            )
+            self.nr_buffer: torch.Tensor = self.sola_buffer.clone()
+            self.output_buffer: torch.Tensor = self.input_wav.clone()
+            self.res_buffer: torch.Tensor = torch.zeros(2 * self.zc, device=device,dtype=torch.float32)
+            self.valid_rate = 1 - (self.extra_frame - 1) / self.input_wav.shape[0]
+            self.fade_in_window: torch.Tensor = (
+                torch.sin(
+                    0.5
+                    * np.pi
+                    * torch.linspace(
+                        0.0,
+                        1.0,
+                        steps=self.crossfade_frame,
+                        device=device,
+                        dtype=torch.float32,
+                    )
+                )
+                ** 2
+            )
+            self.fade_out_window: torch.Tensor = 1 - self.fade_in_window
+            self.resampler = tat.Resample(
+                orig_freq=self.config.samplerate, new_freq=16000, dtype=torch.float32
+            ).to(device)
+            self.tg = TorchGate(sr=self.config.samplerate, n_fft=4*self.zc, prop_decrease=0.9).to(device)
+            thread_vc = threading.Thread(target=self.soundinput)
+            thread_vc.start()
+
+        def soundinput(self):
+            """
+            接受音频输入
+            """
+            channels = 1 if sys.platform == "darwin" else 2
+            with sd.Stream(
+                channels=channels,
+                callback=self.audio_callback,
+                blocksize=self.block_frame,
+                samplerate=self.config.samplerate,
+                dtype="float32",
+            ):
+                while self.flag_vc:
+                    time.sleep(self.config.block_time)
+                    logger.debug("Audio block passed.")
+            logger.debug("ENDing VC")
+
+        def audio_callback(
+            self, indata: np.ndarray, outdata: np.ndarray, frames, times, status
+        ):
+            """
+            音频处理
+            """
+            start_time = time.perf_counter()
+            indata = librosa.to_mono(indata.T)
+            if self.config.threhold > -60:
+                rms = librosa.feature.rms(
+                y=indata, frame_length=4*self.zc, hop_length=self.zc
+                )
+                db_threhold = (
+                    librosa.amplitude_to_db(rms, ref=1.0)[0] < self.config.threhold
+                )
+                for i in range(db_threhold.shape[0]):
+                    if db_threhold[i]:
+                        indata[i * self.zc : (i + 1) * self.zc] = 0
+            self.input_wav[: -self.block_frame] = self.input_wav[self.block_frame :].clone()
+            self.input_wav[-self.block_frame: ] = torch.from_numpy(indata).to(device)
+            self.input_wav_res[ : -self.block_frame_16k] = self.input_wav_res[self.block_frame_16k :].clone()
+            # input noise reduction and resampling
+            if self.config.I_noise_reduce:
+                input_wav = self.input_wav[-self.crossfade_frame -self.block_frame-2*self.zc: ]
+                input_wav = self.tg(input_wav.unsqueeze(0), self.input_wav.unsqueeze(0))[0, 2*self.zc:]
+                input_wav[: self.crossfade_frame] *= self.fade_in_window
+                input_wav[: self.crossfade_frame] += self.nr_buffer * self.fade_out_window
+                self.nr_buffer[:] = input_wav[-self.crossfade_frame: ]
+                input_wav = torch.cat((self.res_buffer[:], input_wav[: self.block_frame]))
+                self.res_buffer[:] = input_wav[-2*self.zc: ]
+                self.input_wav_res[-self.block_frame_16k-160: ] = self.resampler(input_wav)[160: ]
+            else:
+                self.input_wav_res[-self.block_frame_16k-160: ] = self.resampler(self.input_wav[-self.block_frame-2*self.zc: ])[160: ]
+            # infer
+            f0_extractor_frame = self.block_frame_16k + 800
+            if self.config.f0method == 'rmvpe':
+                f0_extractor_frame = 5120 * ((f0_extractor_frame - 1) // 5120 + 1)
+            infer_wav = self.rvc.infer(
+                self.input_wav_res,
+                self.input_wav_res[-f0_extractor_frame :].cpu().numpy(),
+                self.block_frame_16k,
+                self.valid_rate,
+                self.pitch,
+                self.pitchf,
+                self.config.f0method,
+            )
+            infer_wav = infer_wav[
+                -self.crossfade_frame - self.sola_search_frame - self.block_frame :
+            ]
+            # output noise reduction
+            if self.config.O_noise_reduce:
+                self.output_buffer[: -self.block_frame] = self.output_buffer[self.block_frame :].clone()
+                self.output_buffer[-self.block_frame: ] = infer_wav[-self.block_frame:]
+                infer_wav = self.tg(infer_wav.unsqueeze(0), self.output_buffer.unsqueeze(0)).squeeze(0)
+            # volume envelop mixing
+            if self.config.rms_mix_rate < 1:
+                rms1 = librosa.feature.rms(
+                y=self.input_wav_res[-160*infer_wav.shape[0]//self.zc :].cpu().numpy(), 
+                frame_length=640, 
+                hop_length=160,
+                )
+                rms1 = torch.from_numpy(rms1).to(device)
+                rms1 = F.interpolate(
+                    rms1.unsqueeze(0), size=infer_wav.shape[0] + 1, mode="linear",align_corners=True,
+                )[0,0,:-1]
+                rms2 = librosa.feature.rms(
+                y=infer_wav[:].cpu().numpy(), frame_length=4*self.zc, hop_length=self.zc
+                )
+                rms2 = torch.from_numpy(rms2).to(device)
+                rms2 = F.interpolate(
+                    rms2.unsqueeze(0), size=infer_wav.shape[0] + 1, mode="linear",align_corners=True,
+                )[0,0,:-1]
+                rms2 = torch.max(rms2, torch.zeros_like(rms2) + 1e-3)
+                infer_wav *= torch.pow(rms1 / rms2, torch.tensor(1 - self.config.rms_mix_rate))
+            # SOLA algorithm from https://github.com/yxlllc/DDSP-SVC
+            conv_input = infer_wav[None, None, : self.crossfade_frame + self.sola_search_frame]
+            cor_nom = F.conv1d(conv_input, self.sola_buffer[None, None, :])
+            cor_den = torch.sqrt(
+                F.conv1d(conv_input ** 2, torch.ones(1, 1, self.crossfade_frame, device=device)) + 1e-8)
+            if sys.platform == "darwin":
+                _, sola_offset = torch.max(cor_nom[0, 0] / cor_den[0, 0])
+                sola_offset = sola_offset.item()
+            else:
+                sola_offset = torch.argmax(cor_nom[0, 0] / cor_den[0, 0])
+            logger.debug("sola_offset = %d", int(sola_offset))
+            infer_wav = infer_wav[sola_offset: sola_offset + self.block_frame + self.crossfade_frame]
+            infer_wav[: self.crossfade_frame] *= self.fade_in_window
+            infer_wav[: self.crossfade_frame] += self.sola_buffer *self.fade_out_window
+            self.sola_buffer[:] = infer_wav[-self.crossfade_frame:]
+            if sys.platform == "darwin":
+                outdata[:] = infer_wav[:-self.crossfade_frame].cpu().numpy()[:, np.newaxis]
+            else:
+                outdata[:] = infer_wav[:-self.crossfade_frame].repeat(2, 1).t().cpu().numpy()
+            total_time = time.perf_counter() - start_time
+            self.window["infer_time"].update(int(total_time * 1000))
+            logger.info("Infer time: %.2f", total_time)
+
+        def get_devices(self, update: bool = True):
+            """获取设备列表"""
+            if update:
+                sd._terminate()
+                sd._initialize()
+            devices = sd.query_devices()
+            hostapis = sd.query_hostapis()
+            for hostapi in hostapis:
+                for device_idx in hostapi["devices"]:
+                    devices[device_idx]["hostapi_name"] = hostapi["name"]
+            input_devices = [
+                f"{d['name']} ({d['hostapi_name']})"
+                for d in devices
+                if d["max_input_channels"] > 0
+            ]
+            output_devices = [
+                f"{d['name']} ({d['hostapi_name']})"
+                for d in devices
+                if d["max_output_channels"] > 0
+            ]
+            input_devices_indices = [
+                d["index"] if "index" in d else d["name"]
+                for d in devices
+                if d["max_input_channels"] > 0
+            ]
+            output_devices_indices = [
+                d["index"] if "index" in d else d["name"]
+                for d in devices
+                if d["max_output_channels"] > 0
+            ]
+            return (
+                input_devices,
+                output_devices,
+                input_devices_indices,
+                output_devices_indices,
+            )
+
+        def set_devices(self, input_device, output_device):
+            """设置输出设备"""
+            (
+                input_devices,
+                output_devices,
+                input_device_indices,
+                output_device_indices,
+            ) = self.get_devices()
+            sd.default.device[0] = input_device_indices[
+                input_devices.index(input_device)
+            ]
+            sd.default.device[1] = output_device_indices[
+                output_devices.index(output_device)
+            ]
+            logger.info(
+                "Input device: %s:%s", str(sd.default.device[0]), input_device
+            )
+            logger.info(
+                "Output device: %s:%s", str(sd.default.device[1]), output_device
+            )
+
+    gui = GUI()

infer-web.py

@@ -0,0 +1,1505 @@
+import os, sys
+
+now_dir = os.getcwd()
+sys.path.append(now_dir)
+import logging
+import shutil
+import threading
+import traceback
+import warnings
+from random import shuffle
+from subprocess import Popen
+from time import sleep
+import json
+import pathlib
+
+import fairseq
+import faiss
+import gradio as gr
+import numpy as np
+import torch
+from dotenv import load_dotenv
+from sklearn.cluster import MiniBatchKMeans
+
+from configs.config import Config
+from i18n.i18n import I18nAuto
+from infer.lib.train.process_ckpt import (
+    change_info,
+    extract_small_model,
+    merge,
+    show_info,
+)
+from infer.modules.uvr5.modules import uvr
+from infer.modules.vc.modules import VC
+
+logging.getLogger("numba").setLevel(logging.WARNING)
+
+logger = logging.getLogger(__name__)
+
+tmp = os.path.join(now_dir, "TEMP")
+shutil.rmtree(tmp, ignore_errors=True)
+shutil.rmtree("%s/runtime/Lib/site-packages/infer_pack" % (now_dir), ignore_errors=True)
+shutil.rmtree("%s/runtime/Lib/site-packages/uvr5_pack" % (now_dir), ignore_errors=True)
+os.makedirs(tmp, exist_ok=True)
+os.makedirs(os.path.join(now_dir, "logs"), exist_ok=True)
+os.makedirs(os.path.join(now_dir, "assets/weights"), exist_ok=True)
+os.environ["TEMP"] = tmp
+warnings.filterwarnings("ignore")
+torch.manual_seed(114514)
+
+
+load_dotenv()
+config = Config()
+vc = VC(config)
+
+
+if config.dml == True:
+
+    def forward_dml(ctx, x, scale):
+        ctx.scale = scale
+        res = x.clone().detach()
+        return res
+
+    fairseq.modules.grad_multiply.GradMultiply.forward = forward_dml
+i18n = I18nAuto()
+logger.info(i18n)
+# 判断是否有能用来训练和加速推理的N卡
+ngpu = torch.cuda.device_count()
+gpu_infos = []
+mem = []
+if_gpu_ok = False
+
+if torch.cuda.is_available() or ngpu != 0:
+    for i in range(ngpu):
+        gpu_name = torch.cuda.get_device_name(i)
+        if any(
+            value in gpu_name.upper()
+            for value in [
+                "10",
+                "16",
+                "20",
+                "30",
+                "40",
+                "A2",
+                "A3",
+                "A4",
+                "P4",
+                "A50",
+                "500",
+                "A60",
+                "70",
+                "80",
+                "90",
+                "M4",
+                "T4",
+                "TITAN",
+            ]
+        ):
+            # A10#A100#V100#A40#P40#M40#K80#A4500
+            if_gpu_ok = True  # 至少有一张能用的N卡
+            gpu_infos.append("%s\t%s" % (i, gpu_name))
+            mem.append(
+                int(
+                    torch.cuda.get_device_properties(i).total_memory
+                    / 1024
+                    / 1024
+                    / 1024
+                    + 0.4
+                )
+            )
+if if_gpu_ok and len(gpu_infos) > 0:
+    gpu_info = "\n".join(gpu_infos)
+    default_batch_size = min(mem) // 2
+else:
+    gpu_info = i18n("很遗憾您这没有能用的显卡来支持您训练")
+    default_batch_size = 1
+gpus = "-".join([i[0] for i in gpu_infos])
+
+
+class ToolButton(gr.Button, gr.components.FormComponent):
+    """Small button with single emoji as text, fits inside gradio forms"""
+
+    def __init__(self, **kwargs):
+        super().__init__(variant="tool", **kwargs)
+
+    def get_block_name(self):
+        return "button"
+
+
+weight_root = os.getenv("weight_root")
+weight_uvr5_root = os.getenv("weight_uvr5_root")
+index_root = os.getenv("index_root")
+
+names = []
+for name in os.listdir(weight_root):
+    if name.endswith(".pth"):
+        names.append(name)
+index_paths = []
+for root, dirs, files in os.walk(index_root, topdown=False):
+    for name in files:
+        if name.endswith(".index") and "trained" not in name:
+            index_paths.append("%s/%s" % (root, name))
+uvr5_names = []
+for name in os.listdir(weight_uvr5_root):
+    if name.endswith(".pth") or "onnx" in name:
+        uvr5_names.append(name.replace(".pth", ""))
+
+
+def change_choices():
+    names = []
+    for name in os.listdir(weight_root):
+        if name.endswith(".pth"):
+            names.append(name)
+    index_paths = []
+    for root, dirs, files in os.walk(index_root, topdown=False):
+        for name in files:
+            if name.endswith(".index") and "trained" not in name:
+                index_paths.append("%s/%s" % (root, name))
+    return {"choices": sorted(names), "__type__": "update"}, {
+        "choices": sorted(index_paths),
+        "__type__": "update",
+    }
+
+
+def clean():
+    return {"value": "", "__type__": "update"}
+
+
+def export_onnx():
+    from infer.modules.onnx.export import export_onnx as eo
+
+    eo()
+
+
+sr_dict = {
+    "32k": 32000,
+    "40k": 40000,
+    "48k": 48000,
+}
+
+
+def if_done(done, p):
+    while 1:
+        if p.poll() is None:
+            sleep(0.5)
+        else:
+            break
+    done[0] = True
+
+
+def if_done_multi(done, ps):
+    while 1:
+        # poll==None代表进程未结束
+        # 只要有一个进程未结束都不停
+        flag = 1
+        for p in ps:
+            if p.poll() is None:
+                flag = 0
+                sleep(0.5)
+                break
+        if flag == 1:
+            break
+    done[0] = True
+
+
+def preprocess_dataset(trainset_dir, exp_dir, sr, n_p):
+    sr = sr_dict[sr]
+    os.makedirs("%s/logs/%s" % (now_dir, exp_dir), exist_ok=True)
+    f = open("%s/logs/%s/preprocess.log" % (now_dir, exp_dir), "w")
+    f.close()
+    per = 3.0 if config.is_half else 3.7
+    cmd = '"%s" infer/modules/train/preprocess.py "%s" %s %s "%s/logs/%s" %s %.1f' % (
+        config.python_cmd,
+        trainset_dir,
+        sr,
+        n_p,
+        now_dir,
+        exp_dir,
+        config.noparallel,
+        per,
+    )
+    logger.info(cmd)
+    p = Popen(cmd, shell=True)  # , stdin=PIPE, stdout=PIPE,stderr=PIPE,cwd=now_dir
+    ###煞笔gr, popen read都非得全跑完了再一次性读取, 不用gr就正常读一句输出一句;只能额外弄出一个文本流定时读
+    done = [False]
+    threading.Thread(
+        target=if_done,
+        args=(
+            done,
+            p,
+        ),
+    ).start()
+    while 1:
+        with open("%s/logs/%s/preprocess.log" % (now_dir, exp_dir), "r") as f:
+            yield (f.read())
+        sleep(1)
+        if done[0]:
+            break
+    with open("%s/logs/%s/preprocess.log" % (now_dir, exp_dir), "r") as f:
+        log = f.read()
+    logger.info(log)
+    yield log
+
+
+# but2.click(extract_f0,[gpus6,np7,f0method8,if_f0_3,trainset_dir4],[info2])
+def extract_f0_feature(gpus, n_p, f0method, if_f0, exp_dir, version19, gpus_rmvpe):
+    gpus = gpus.split("-")
+    os.makedirs("%s/logs/%s" % (now_dir, exp_dir), exist_ok=True)
+    f = open("%s/logs/%s/extract_f0_feature.log" % (now_dir, exp_dir), "w")
+    f.close()
+    if if_f0:
+        if f0method != "rmvpe_gpu":
+            cmd = (
+                '"%s" infer/modules/train/extract/extract_f0_print.py "%s/logs/%s" %s %s'
+                % (
+                    config.python_cmd,
+                    now_dir,
+                    exp_dir,
+                    n_p,
+                    f0method,
+                )
+            )
+            logger.info(cmd)
+            p = Popen(
+                cmd, shell=True, cwd=now_dir
+            )  # , stdin=PIPE, stdout=PIPE,stderr=PIPE
+            ###煞笔gr, popen read都非得全跑完了再一次性读取, 不用gr就正常读一句输出一句;只能额外弄出一个文本流定时读
+            done = [False]
+            threading.Thread(
+                target=if_done,
+                args=(
+                    done,
+                    p,
+                ),
+            ).start()
+        else:
+            if gpus_rmvpe != "-":
+                gpus_rmvpe = gpus_rmvpe.split("-")
+                leng = len(gpus_rmvpe)
+                ps = []
+                for idx, n_g in enumerate(gpus_rmvpe):
+                    cmd = (
+                        '"%s" infer/modules/train/extract/extract_f0_rmvpe.py %s %s %s "%s/logs/%s" %s '
+                        % (
+                            config.python_cmd,
+                            leng,
+                            idx,
+                            n_g,
+                            now_dir,
+                            exp_dir,
+                            config.is_half,
+                        )
+                    )
+                    logger.info(cmd)
+                    p = Popen(
+                        cmd, shell=True, cwd=now_dir
+                    )  # , shell=True, stdin=PIPE, stdout=PIPE, stderr=PIPE, cwd=now_dir
+                    ps.append(p)
+                ###煞笔gr, popen read都非得全跑完了再一次性读取, 不用gr就正常读一句输出一句;只能额外弄出一个文本流定时读
+                done = [False]
+                threading.Thread(
+                    target=if_done_multi,  #
+                    args=(
+                        done,
+                        ps,
+                    ),
+                ).start()
+            else:
+                cmd = (
+                    config.python_cmd
+                    + ' infer/modules/train/extract/extract_f0_rmvpe_dml.py "%s/logs/%s" '
+                    % (
+                        now_dir,
+                        exp_dir,
+                    )
+                )
+                logger.info(cmd)
+                p = Popen(
+                    cmd, shell=True, cwd=now_dir
+                )  # , shell=True, stdin=PIPE, stdout=PIPE, stderr=PIPE, cwd=now_dir
+                p.wait()
+                done = [True]
+        while 1:
+            with open(
+                "%s/logs/%s/extract_f0_feature.log" % (now_dir, exp_dir), "r"
+            ) as f:
+                yield (f.read())
+            sleep(1)
+            if done[0]:
+                break
+        with open("%s/logs/%s/extract_f0_feature.log" % (now_dir, exp_dir), "r") as f:
+            log = f.read()
+        logger.info(log)
+        yield log
+    ####对不同part分别开多进程
+    """
+    n_part=int(sys.argv[1])
+    i_part=int(sys.argv[2])
+    i_gpu=sys.argv[3]
+    exp_dir=sys.argv[4]
+    os.environ["CUDA_VISIBLE_DEVICES"]=str(i_gpu)
+    """
+    leng = len(gpus)
+    ps = []
+    for idx, n_g in enumerate(gpus):
+        cmd = (
+            '"%s" infer/modules/train/extract_feature_print.py %s %s %s %s "%s/logs/%s" %s'
+            % (
+                config.python_cmd,
+                config.device,
+                leng,
+                idx,
+                n_g,
+                now_dir,
+                exp_dir,
+                version19,
+            )
+        )
+        logger.info(cmd)
+        p = Popen(
+            cmd, shell=True, cwd=now_dir
+        )  # , shell=True, stdin=PIPE, stdout=PIPE, stderr=PIPE, cwd=now_dir
+        ps.append(p)
+    ###煞笔gr, popen read都非得全跑完了再一次性读取, 不用gr就正常读一句输出一句;只能额外弄出一个文本流定时读
+    done = [False]
+    threading.Thread(
+        target=if_done_multi,
+        args=(
+            done,
+            ps,
+        ),
+    ).start()
+    while 1:
+        with open("%s/logs/%s/extract_f0_feature.log" % (now_dir, exp_dir), "r") as f:
+            yield (f.read())
+        sleep(1)
+        if done[0]:
+            break
+    with open("%s/logs/%s/extract_f0_feature.log" % (now_dir, exp_dir), "r") as f:
+        log = f.read()
+    logger.info(log)
+    yield log
+
+
+def get_pretrained_models(path_str, f0_str, sr2):
+    if_pretrained_generator_exist = os.access(
+        "assets/pretrained%s/%sG%s.pth" % (path_str, f0_str, sr2), os.F_OK
+    )
+    if_pretrained_discriminator_exist = os.access(
+        "assets/pretrained%s/%sD%s.pth" % (path_str, f0_str, sr2), os.F_OK
+    )
+    if not if_pretrained_generator_exist:
+        logger.warn(
+            "assets/pretrained%s/%sG%s.pth not exist, will not use pretrained model",
+            path_str,
+            f0_str,
+            sr2,
+        )
+    if not if_pretrained_discriminator_exist:
+        logger.warn(
+            "assets/pretrained%s/%sD%s.pth not exist, will not use pretrained model",
+            path_str,
+            f0_str,
+            sr2,
+        )
+    return (
+        "assets/pretrained%s/%sG%s.pth" % (path_str, f0_str, sr2)
+        if if_pretrained_generator_exist
+        else "",
+        "assets/pretrained%s/%sD%s.pth" % (path_str, f0_str, sr2)
+        if if_pretrained_discriminator_exist
+        else "",
+    )
+
+
+def change_sr2(sr2, if_f0_3, version19):
+    path_str = "" if version19 == "v1" else "_v2"
+    f0_str = "f0" if if_f0_3 else ""
+    return get_pretrained_models(path_str, f0_str, sr2)
+
+
+def change_version19(sr2, if_f0_3, version19):
+    path_str = "" if version19 == "v1" else "_v2"
+    if sr2 == "32k" and version19 == "v1":
+        sr2 = "40k"
+    to_return_sr2 = (
+        {"choices": ["40k", "48k"], "__type__": "update", "value": sr2}
+        if version19 == "v1"
+        else {"choices": ["40k", "48k", "32k"], "__type__": "update", "value": sr2}
+    )
+    f0_str = "f0" if if_f0_3 else ""
+    return (
+        *get_pretrained_models(path_str, f0_str, sr2),
+        to_return_sr2,
+    )
+
+
+def change_f0(if_f0_3, sr2, version19):  # f0method8,pretrained_G14,pretrained_D15
+    path_str = "" if version19 == "v1" else "_v2"
+    return (
+        {"visible": if_f0_3, "__type__": "update"},
+        *get_pretrained_models(path_str, "f0", sr2),
+    )
+
+
+# but3.click(click_train,[exp_dir1,sr2,if_f0_3,save_epoch10,total_epoch11,batch_size12,if_save_latest13,pretrained_G14,pretrained_D15,gpus16])
+def click_train(
+    exp_dir1,
+    sr2,
+    if_f0_3,
+    spk_id5,
+    save_epoch10,
+    total_epoch11,
+    batch_size12,
+    if_save_latest13,
+    pretrained_G14,
+    pretrained_D15,
+    gpus16,
+    if_cache_gpu17,
+    if_save_every_weights18,
+    version19,
+):
+    # 生成filelist
+    exp_dir = "%s/logs/%s" % (now_dir, exp_dir1)
+    os.makedirs(exp_dir, exist_ok=True)
+    gt_wavs_dir = "%s/0_gt_wavs" % (exp_dir)
+    feature_dir = (
+        "%s/3_feature256" % (exp_dir)
+        if version19 == "v1"
+        else "%s/3_feature768" % (exp_dir)
+    )
+    if if_f0_3:
+        f0_dir = "%s/2a_f0" % (exp_dir)
+        f0nsf_dir = "%s/2b-f0nsf" % (exp_dir)
+        names = (
+            set([name.split(".")[0] for name in os.listdir(gt_wavs_dir)])
+            & set([name.split(".")[0] for name in os.listdir(feature_dir)])
+            & set([name.split(".")[0] for name in os.listdir(f0_dir)])
+            & set([name.split(".")[0] for name in os.listdir(f0nsf_dir)])
+        )
+    else:
+        names = set([name.split(".")[0] for name in os.listdir(gt_wavs_dir)]) & set(
+            [name.split(".")[0] for name in os.listdir(feature_dir)]
+        )
+    opt = []
+    for name in names:
+        if if_f0_3:
+            opt.append(
+                "%s/%s.wav|%s/%s.npy|%s/%s.wav.npy|%s/%s.wav.npy|%s"
+                % (
+                    gt_wavs_dir.replace("\\", "\\\\"),
+                    name,
+                    feature_dir.replace("\\", "\\\\"),
+                    name,
+                    f0_dir.replace("\\", "\\\\"),
+                    name,
+                    f0nsf_dir.replace("\\", "\\\\"),
+                    name,
+                    spk_id5,
+                )
+            )
+        else:
+            opt.append(
+                "%s/%s.wav|%s/%s.npy|%s"
+                % (
+                    gt_wavs_dir.replace("\\", "\\\\"),
+                    name,
+                    feature_dir.replace("\\", "\\\\"),
+                    name,
+                    spk_id5,
+                )
+            )
+    fea_dim = 256 if version19 == "v1" else 768
+    if if_f0_3:
+        for _ in range(2):
+            opt.append(
+                "%s/logs/mute/0_gt_wavs/mute%s.wav|%s/logs/mute/3_feature%s/mute.npy|%s/logs/mute/2a_f0/mute.wav.npy|%s/logs/mute/2b-f0nsf/mute.wav.npy|%s"
+                % (now_dir, sr2, now_dir, fea_dim, now_dir, now_dir, spk_id5)
+            )
+    else:
+        for _ in range(2):
+            opt.append(
+                "%s/logs/mute/0_gt_wavs/mute%s.wav|%s/logs/mute/3_feature%s/mute.npy|%s"
+                % (now_dir, sr2, now_dir, fea_dim, spk_id5)
+            )
+    shuffle(opt)
+    with open("%s/filelist.txt" % exp_dir, "w") as f:
+        f.write("\n".join(opt))
+    logger.debug("Write filelist done")
+    # 生成config#无需生成config
+    # cmd = python_cmd + " train_nsf_sim_cache_sid_load_pretrain.py -e mi-test -sr 40k -f0 1 -bs 4 -g 0 -te 10 -se 5 -pg pretrained/f0G40k.pth -pd pretrained/f0D40k.pth -l 1 -c 0"
+    logger.info("Use gpus: %s", str(gpus16))
+    if pretrained_G14 == "":
+        logger.info("No pretrained Generator")
+    if pretrained_D15 == "":
+        logger.info("No pretrained Discriminator")
+    if version19 == "v1" or sr2 == "40k":
+        config_path = "v1/%s.json" % sr2
+    else:
+        config_path = "v2/%s.json" % sr2
+    config_save_path = os.path.join(exp_dir, "config.json")
+    if not pathlib.Path(config_save_path).exists():
+        with open(config_save_path, "w", encoding="utf-8") as f:
+            json.dump(
+                config.json_config[config_path],
+                f,
+                ensure_ascii=False,
+                indent=4,
+                sort_keys=True,
+            )
+            f.write("\n")
+    if gpus16:
+        cmd = (
+            '"%s" infer/modules/train/train.py -e "%s" -sr %s -f0 %s -bs %s -g %s -te %s -se %s %s %s -l %s -c %s -sw %s -v %s'
+            % (
+                config.python_cmd,
+                exp_dir1,
+                sr2,
+                1 if if_f0_3 else 0,
+                batch_size12,
+                gpus16,
+                total_epoch11,
+                save_epoch10,
+                "-pg %s" % pretrained_G14 if pretrained_G14 != "" else "",
+                "-pd %s" % pretrained_D15 if pretrained_D15 != "" else "",
+                1 if if_save_latest13 == i18n("是") else 0,
+                1 if if_cache_gpu17 == i18n("是") else 0,
+                1 if if_save_every_weights18 == i18n("是") else 0,
+                version19,
+            )
+        )
+    else:
+        cmd = (
+            '"%s" infer/modules/train/train.py -e "%s" -sr %s -f0 %s -bs %s -te %s -se %s %s %s -l %s -c %s -sw %s -v %s'
+            % (
+                config.python_cmd,
+                exp_dir1,
+                sr2,
+                1 if if_f0_3 else 0,
+                batch_size12,
+                total_epoch11,
+                save_epoch10,
+                "-pg %s" % pretrained_G14 if pretrained_G14 != "" else "",
+                "-pd %s" % pretrained_D15 if pretrained_D15 != "" else "",
+                1 if if_save_latest13 == i18n("是") else 0,
+                1 if if_cache_gpu17 == i18n("是") else 0,
+                1 if if_save_every_weights18 == i18n("是") else 0,
+                version19,
+            )
+        )
+    logger.info(cmd)
+    p = Popen(cmd, shell=True, cwd=now_dir)
+    p.wait()
+    return "训练结束, 您可查看控制台训练日志或实验文件夹下的train.log"
+
+
+# but4.click(train_index, [exp_dir1], info3)
+def train_index(exp_dir1, version19):
+    # exp_dir = "%s/logs/%s" % (now_dir, exp_dir1)
+    exp_dir = "logs/%s" % (exp_dir1)
+    os.makedirs(exp_dir, exist_ok=True)
+    feature_dir = (
+        "%s/3_feature256" % (exp_dir)
+        if version19 == "v1"
+        else "%s/3_feature768" % (exp_dir)
+    )
+    if not os.path.exists(feature_dir):
+        return "请先进行特征提取!"
+    listdir_res = list(os.listdir(feature_dir))
+    if len(listdir_res) == 0:
+        return "请先进行特征提取！"
+    infos = []
+    npys = []
+    for name in sorted(listdir_res):
+        phone = np.load("%s/%s" % (feature_dir, name))
+        npys.append(phone)
+    big_npy = np.concatenate(npys, 0)
+    big_npy_idx = np.arange(big_npy.shape[0])
+    np.random.shuffle(big_npy_idx)
+    big_npy = big_npy[big_npy_idx]
+    if big_npy.shape[0] > 2e5:
+        infos.append("Trying doing kmeans %s shape to 10k centers." % big_npy.shape[0])
+        yield "\n".join(infos)
+        try:
+            big_npy = (
+                MiniBatchKMeans(
+                    n_clusters=10000,
+                    verbose=True,
+                    batch_size=256 * config.n_cpu,
+                    compute_labels=False,
+                    init="random",
+                )
+                .fit(big_npy)
+                .cluster_centers_
+            )
+        except:
+            info = traceback.format_exc()
+            logger.info(info)
+            infos.append(info)
+            yield "\n".join(infos)
+
+    np.save("%s/total_fea.npy" % exp_dir, big_npy)
+    n_ivf = min(int(16 * np.sqrt(big_npy.shape[0])), big_npy.shape[0] // 39)
+    infos.append("%s,%s" % (big_npy.shape, n_ivf))
+    yield "\n".join(infos)
+    index = faiss.index_factory(256 if version19 == "v1" else 768, "IVF%s,Flat" % n_ivf)
+    # index = faiss.index_factory(256if version19=="v1"else 768, "IVF%s,PQ128x4fs,RFlat"%n_ivf)
+    infos.append("training")
+    yield "\n".join(infos)
+    index_ivf = faiss.extract_index_ivf(index)  #
+    index_ivf.nprobe = 1
+    index.train(big_npy)
+    faiss.write_index(
+        index,
+        "%s/trained_IVF%s_Flat_nprobe_%s_%s_%s.index"
+        % (exp_dir, n_ivf, index_ivf.nprobe, exp_dir1, version19),
+    )
+
+    infos.append("adding")
+    yield "\n".join(infos)
+    batch_size_add = 8192
+    for i in range(0, big_npy.shape[0], batch_size_add):
+        index.add(big_npy[i : i + batch_size_add])
+    faiss.write_index(
+        index,
+        "%s/added_IVF%s_Flat_nprobe_%s_%s_%s.index"
+        % (exp_dir, n_ivf, index_ivf.nprobe, exp_dir1, version19),
+    )
+    infos.append(
+        "成功构建索引，added_IVF%s_Flat_nprobe_%s_%s_%s.index"
+        % (n_ivf, index_ivf.nprobe, exp_dir1, version19)
+    )
+    # faiss.write_index(index, '%s/added_IVF%s_Flat_FastScan_%s.index'%(exp_dir,n_ivf,version19))
+    # infos.append("成功构建索引，added_IVF%s_Flat_FastScan_%s.index"%(n_ivf,version19))
+    yield "\n".join(infos)
+
+
+# but5.click(train1key, [exp_dir1, sr2, if_f0_3, trainset_dir4, spk_id5, gpus6, np7, f0method8, save_epoch10, total_epoch11, batch_size12, if_save_latest13, pretrained_G14, pretrained_D15, gpus16, if_cache_gpu17], info3)
+def train1key(
+    exp_dir1,
+    sr2,
+    if_f0_3,
+    trainset_dir4,
+    spk_id5,
+    np7,
+    f0method8,
+    save_epoch10,
+    total_epoch11,
+    batch_size12,
+    if_save_latest13,
+    pretrained_G14,
+    pretrained_D15,
+    gpus16,
+    if_cache_gpu17,
+    if_save_every_weights18,
+    version19,
+    gpus_rmvpe,
+):
+    infos = []
+
+    def get_info_str(strr):
+        infos.append(strr)
+        return "\n".join(infos)
+
+    ####### step1:处理数据
+    yield get_info_str(i18n("step1:正在处理数据"))
+    [get_info_str(_) for _ in preprocess_dataset(trainset_dir4, exp_dir1, sr2, np7)]
+
+    ####### step2a:提取音高
+    yield get_info_str(i18n("step2:正在提取音高&正在提取特征"))
+    [
+        get_info_str(_)
+        for _ in extract_f0_feature(
+            gpus16, np7, f0method8, if_f0_3, exp_dir1, version19, gpus_rmvpe
+        )
+    ]
+
+    ####### step3a:训练模型
+    yield get_info_str(i18n("step3a:正在训练模型"))
+    click_train(
+        exp_dir1,
+        sr2,
+        if_f0_3,
+        spk_id5,
+        save_epoch10,
+        total_epoch11,
+        batch_size12,
+        if_save_latest13,
+        pretrained_G14,
+        pretrained_D15,
+        gpus16,
+        if_cache_gpu17,
+        if_save_every_weights18,
+        version19,
+    )
+    yield get_info_str(i18n("训练结束, 您可查看控制台训练日志或实验文件夹下的train.log"))
+
+    ####### step3b:训练索引
+    [get_info_str(_) for _ in train_index(exp_dir1, version19)]
+    yield get_info_str(i18n("全流程结束！"))
+
+
+#                    ckpt_path2.change(change_info_,[ckpt_path2],[sr__,if_f0__])
+def change_info_(ckpt_path):
+    if not os.path.exists(ckpt_path.replace(os.path.basename(ckpt_path), "train.log")):
+        return {"__type__": "update"}, {"__type__": "update"}, {"__type__": "update"}
+    try:
+        with open(
+            ckpt_path.replace(os.path.basename(ckpt_path), "train.log"), "r"
+        ) as f:
+            info = eval(f.read().strip("\n").split("\n")[0].split("\t")[-1])
+            sr, f0 = info["sample_rate"], info["if_f0"]
+            version = "v2" if ("version" in info and info["version"] == "v2") else "v1"
+            return sr, str(f0), version
+    except:
+        traceback.print_exc()
+        return {"__type__": "update"}, {"__type__": "update"}, {"__type__": "update"}
+
+
+F0GPUVisible = config.dml == False
+
+
+def change_f0_method(f0method8):
+    if f0method8 == "rmvpe_gpu":
+        visible = F0GPUVisible
+    else:
+        visible = False
+    return {"visible": visible, "__type__": "update"}
+
+
+with gr.Blocks(title="RVC WebUI") as app:
+    gr.Markdown(
+        value=i18n(
+            "本软件以MIT协议开源, 作者不对软件具备任何控制力, 使用软件者、传播软件导出的声音者自负全责. <br>如不认可该���款, 则不能使用或引用软件包内任何代码和文件. 详见根目录<b>LICENSE</b>."
+        )
+    )
+    with gr.Tabs():
+        with gr.TabItem(i18n("模型推理")):
+            with gr.Row():
+                sid0 = gr.Dropdown(label=i18n("推理音色"), choices=sorted(names))
+                refresh_button = gr.Button(i18n("刷新音色列表和索引路径"), variant="primary")
+                clean_button = gr.Button(i18n("卸载音色省显存"), variant="primary")
+                spk_item = gr.Slider(
+                    minimum=0,
+                    maximum=2333,
+                    step=1,
+                    label=i18n("请选择说话人id"),
+                    value=0,
+                    visible=False,
+                    interactive=True,
+                )
+                clean_button.click(
+                    fn=clean, inputs=[], outputs=[sid0], api_name="infer_clean"
+                )
+            with gr.Group():
+                gr.Markdown(
+                    value=i18n("男转女推荐+12key, 女转男推荐-12key, 如果音域爆炸导致音色失真也可以自己调整到合适音域. ")
+                )
+                with gr.Row():
+                    with gr.Column():
+                        vc_transform0 = gr.Number(
+                            label=i18n("变调(整数, 半音数量, 升八度12降八度-12)"), value=0
+                        )
+                        input_audio0 = gr.Textbox(
+                            label=i18n("输入待处理音频文件路径(默认是正确格式示例)"),
+                            value="E:\\codes\\py39\\test-20230416b\\todo-songs\\冬之花clip1.wav",
+                        )
+                        f0method0 = gr.Radio(
+                            label=i18n(
+                                "选择音高提取算法,输入歌声可用pm提速,harvest低音好但巨慢无比,crepe效果好但吃GPU,rmvpe效果最好且微吃GPU"
+                            ),
+                            choices=["pm", "harvest", "crepe", "rmvpe"]
+                            if config.dml == False
+                            else ["pm", "harvest", "rmvpe"],
+                            value="pm",
+                            interactive=True,
+                        )
+                        filter_radius0 = gr.Slider(
+                            minimum=0,
+                            maximum=7,
+                            label=i18n(">=3则使用对harvest音高识别的结果使用中值滤波，数值为滤波半径，使用可以削弱哑音"),
+                            value=3,
+                            step=1,
+                            interactive=True,
+                        )
+                    with gr.Column():
+                        file_index1 = gr.Textbox(
+                            label=i18n("特征检索库文件路径,为空则使用下拉的选择结果"),
+                            value="",
+                            interactive=True,
+                        )
+                        file_index2 = gr.Dropdown(
+                            label=i18n("自动检测index路径,下拉式选择(dropdown)"),
+                            choices=sorted(index_paths),
+                            interactive=True,
+                        )
+                        refresh_button.click(
+                            fn=change_choices,
+                            inputs=[],
+                            outputs=[sid0, file_index2],
+                            api_name="infer_refresh",
+                        )
+                        # file_big_npy1 = gr.Textbox(
+                        #     label=i18n("特征文件路径"),
+                        #     value="E:\\codes\py39\\vits_vc_gpu_train\\logs\\mi-test-1key\\total_fea.npy",
+                        #     interactive=True,
+                        # )
+                        index_rate1 = gr.Slider(
+                            minimum=0,
+                            maximum=1,
+                            label=i18n("检索特征占比"),
+                            value=0.75,
+                            interactive=True,
+                        )
+                    with gr.Column():
+                        resample_sr0 = gr.Slider(
+                            minimum=0,
+                            maximum=48000,
+                            label=i18n("后处理重采样至最终采样率，0为不进行重采样"),
+                            value=0,
+                            step=1,
+                            interactive=True,
+                        )
+                        rms_mix_rate0 = gr.Slider(
+                            minimum=0,
+                            maximum=1,
+                            label=i18n("输入源音量包络替换输出音量包络融合比例，越靠近1越使用输出包络"),
+                            value=0.25,
+                            interactive=True,
+                        )
+                        protect0 = gr.Slider(
+                            minimum=0,
+                            maximum=0.5,
+                            label=i18n(
+                                "保护清辅音和呼吸声，防止电音撕裂等artifact，拉满0.5不开启，调低加大保护力度但可能降低索引效果"
+                            ),
+                            value=0.33,
+                            step=0.01,
+                            interactive=True,
+                        )
+                    f0_file = gr.File(label=i18n("F0曲线文件, 可选, 一行一个音高, 代替默认F0及升降调"))
+                    but0 = gr.Button(i18n("转换"), variant="primary")
+                    with gr.Row():
+                        vc_output1 = gr.Textbox(label=i18n("输出信息"))
+                        vc_output2 = gr.Audio(label=i18n("输出音频(右下角三个点,点了可以下载)"))
+                    but0.click(
+                        vc.vc_single,
+                        [
+                            spk_item,
+                            input_audio0,
+                            vc_transform0,
+                            f0_file,
+                            f0method0,
+                            file_index1,
+                            file_index2,
+                            # file_big_npy1,
+                            index_rate1,
+                            filter_radius0,
+                            resample_sr0,
+                            rms_mix_rate0,
+                            protect0,
+                        ],
+                        [vc_output1, vc_output2],
+                        api_name="infer_convert",
+                    )
+            with gr.Group():
+                gr.Markdown(
+                    value=i18n("批量转换, 输入待转换音频文件夹, 或上传多个音频文件, 在指定文件夹(默认opt)下输出转换的音频. ")
+                )
+                with gr.Row():
+                    with gr.Column():
+                        vc_transform1 = gr.Number(
+                            label=i18n("变调(整数, 半音数量, 升八度12降八度-12)"), value=0
+                        )
+                        opt_input = gr.Textbox(label=i18n("指定输出文件夹"), value="opt")
+                        f0method1 = gr.Radio(
+                            label=i18n(
+                                "选择音高提取算法,输入歌声可用pm提速,harvest低音好但巨慢无比,crepe效果好但吃GPU,rmvpe效果最好且微吃GPU"
+                            ),
+                            choices=["pm", "harvest", "crepe", "rmvpe"]
+                            if config.dml == False
+                            else ["pm", "harvest", "rmvpe"],
+                            value="pm",
+                            interactive=True,
+                        )
+                        filter_radius1 = gr.Slider(
+                            minimum=0,
+                            maximum=7,
+                            label=i18n(">=3则使用对harvest音高识别的结果使用中值滤波，数值为滤波半径，使用可以削弱哑音"),
+                            value=3,
+                            step=1,
+                            interactive=True,
+                        )
+                    with gr.Column():
+                        file_index3 = gr.Textbox(
+                            label=i18n("特征检索库文件路径,为空则使用下拉的选择结果"),
+                            value="",
+                            interactive=True,
+                        )
+                        file_index4 = gr.Dropdown(
+                            label=i18n("自动检测index路径,下拉式选择(dropdown)"),
+                            choices=sorted(index_paths),
+                            interactive=True,
+                        )
+                        refresh_button.click(
+                            fn=lambda: change_choices()[1],
+                            inputs=[],
+                            outputs=file_index4,
+                            api_name="infer_refresh_batch",
+                        )
+                        # file_big_npy2 = gr.Textbox(
+                        #     label=i18n("特征文件路径"),
+                        #     value="E:\\codes\\py39\\vits_vc_gpu_train\\logs\\mi-test-1key\\total_fea.npy",
+                        #     interactive=True,
+                        # )
+                        index_rate2 = gr.Slider(
+                            minimum=0,
+                            maximum=1,
+                            label=i18n("检索特征占比"),
+                            value=1,
+                            interactive=True,
+                        )
+                    with gr.Column():
+                        resample_sr1 = gr.Slider(
+                            minimum=0,
+                            maximum=48000,
+                            label=i18n("后处理重采样至最终采样率，0为不进行重采样"),
+                            value=0,
+                            step=1,
+                            interactive=True,
+                        )
+                        rms_mix_rate1 = gr.Slider(
+                            minimum=0,
+                            maximum=1,
+                            label=i18n("输入源音量包络替换输出音量包络融合比例，越靠近1越使用输出包络"),
+                            value=1,
+                            interactive=True,
+                        )
+                        protect1 = gr.Slider(
+                            minimum=0,
+                            maximum=0.5,
+                            label=i18n(
+                                "保护清辅音和呼吸声，防止电音撕裂等artifact，拉满0.5不开启，调低加大保护力度但可能降低索引效果"
+                            ),
+                            value=0.33,
+                            step=0.01,
+                            interactive=True,
+                        )
+                    with gr.Column():
+                        dir_input = gr.Textbox(
+                            label=i18n("输入待处理音频文件夹路径(去文件管理器地址栏拷就行了)"),
+                            value="E:\codes\py39\\test-20230416b\\todo-songs",
+                        )
+                        inputs = gr.File(
+                            file_count="multiple", label=i18n("也可批量输入音频文件, 二选一, 优先读文件夹")
+                        )
+                    with gr.Row():
+                        format1 = gr.Radio(
+                            label=i18n("导出文件格式"),
+                            choices=["wav", "flac", "mp3", "m4a"],
+                            value="flac",
+                            interactive=True,
+                        )
+                        but1 = gr.Button(i18n("转换"), variant="primary")
+                        vc_output3 = gr.Textbox(label=i18n("输出信息"))
+                    but1.click(
+                        vc.vc_multi,
+                        [
+                            spk_item,
+                            dir_input,
+                            opt_input,
+                            inputs,
+                            vc_transform1,
+                            f0method1,
+                            file_index3,
+                            file_index4,
+                            # file_big_npy2,
+                            index_rate2,
+                            filter_radius1,
+                            resample_sr1,
+                            rms_mix_rate1,
+                            protect1,
+                            format1,
+                        ],
+                        [vc_output3],
+                        api_name="infer_convert_batch",
+                    )
+            sid0.change(
+                fn=vc.get_vc,
+                inputs=[sid0, protect0, protect1],
+                outputs=[spk_item, protect0, protect1, file_index2, file_index4],
+            )
+        with gr.TabItem(i18n("伴奏人声分离&去混响&去回声")):
+            with gr.Group():
+                gr.Markdown(
+                    value=i18n(
+                        "人声伴奏分离批量处理， 使用UVR5模型。 <br>合格的文件夹路径格式举例： E:\\codes\\py39\\vits_vc_gpu\\白鹭霜华测试样例(去文件管理器地址栏拷就行了)。 <br>模型分为三类： <br>1、保留人声：不带和声的音频选这个，对主人声保留比HP5更好。内置HP2和HP3两个模型，HP3可能轻微漏伴奏但对主人声保留比HP2稍微好一丁点； <br>2、仅保留主人声：带和声的音频选这个，对主人声可能有削弱。内置HP5一个模型； <br> 3、去混响、去延迟模型（by FoxJoy）：<br>  (1)MDX-Net(onnx_dereverb):对于双通道混响是最好的选择，不能去除单通道混响；<br>&emsp;(234)DeEcho:去除延迟效果。Aggressive比Normal去除得更彻底，DeReverb额外去除混响，可去除单声道混响，但是对高频重的板式混响去不干净。<br>去混响/去延迟，附：<br>1、DeEcho-DeReverb模型的耗时是另外2个DeEcho模型的接近2倍；<br>2、MDX-Net-Dereverb模型挺慢的；<br>3、个人推荐的最干净的配置是先MDX-Net再DeEcho-Aggressive。"
+                    )
+                )
+                with gr.Row():
+                    with gr.Column():
+                        dir_wav_input = gr.Textbox(
+                            label=i18n("输入待处理音频文件夹路径"),
+                            value="E:\\codes\\py39\\test-20230416b\\todo-songs\\todo-songs",
+                        )
+                        wav_inputs = gr.File(
+                            file_count="multiple", label=i18n("也可批量输入音频文件, 二选一, 优先读文件夹")
+                        )
+                    with gr.Column():
+                        model_choose = gr.Dropdown(label=i18n("模型"), choices=uvr5_names)
+                        agg = gr.Slider(
+                            minimum=0,
+                            maximum=20,
+                            step=1,
+                            label="人声提取激进程度",
+                            value=10,
+                            interactive=True,
+                            visible=False,  # 先不开放调整
+                        )
+                        opt_vocal_root = gr.Textbox(
+                            label=i18n("指定输出主人声文件夹"), value="opt"
+                        )
+                        opt_ins_root = gr.Textbox(
+                            label=i18n("指定输出非主人声文件夹"), value="opt"
+                        )
+                        format0 = gr.Radio(
+                            label=i18n("导出文件格式"),
+                            choices=["wav", "flac", "mp3", "m4a"],
+                            value="flac",
+                            interactive=True,
+                        )
+                    but2 = gr.Button(i18n("转换"), variant="primary")
+                    vc_output4 = gr.Textbox(label=i18n("输出信息"))
+                    but2.click(
+                        uvr,
+                        [
+                            model_choose,
+                            dir_wav_input,
+                            opt_vocal_root,
+                            wav_inputs,
+                            opt_ins_root,
+                            agg,
+                            format0,
+                        ],
+                        [vc_output4],
+                        api_name="uvr_convert",
+                    )
+        with gr.TabItem(i18n("训练")):
+            gr.Markdown(
+                value=i18n(
+                    "step1: 填写实验配置. 实验数据放在logs下, 每个实验一个文件夹, 需手工输入实验名路径, 内含实验配置, 日志, 训练得到的模型文件. "
+                )
+            )
+            with gr.Row():
+                exp_dir1 = gr.Textbox(label=i18n("输入实验名"), value="mi-test")
+                sr2 = gr.Radio(
+                    label=i18n("目标采样率"),
+                    choices=["40k", "48k"],
+                    value="40k",
+                    interactive=True,
+                )
+                if_f0_3 = gr.Radio(
+                    label=i18n("模型是否带音高指导(唱歌一定要, 语音可以不要)"),
+                    choices=[True, False],
+                    value=True,
+                    interactive=True,
+                )
+                version19 = gr.Radio(
+                    label=i18n("版本"),
+                    choices=["v1", "v2"],
+                    value="v2",
+                    interactive=True,
+                    visible=True,
+                )
+                np7 = gr.Slider(
+                    minimum=0,
+                    maximum=config.n_cpu,
+                    step=1,
+                    label=i18n("提取音高和处理数据使用的CPU进程数"),
+                    value=int(np.ceil(config.n_cpu / 1.5)),
+                    interactive=True,
+                )
+            with gr.Group():  # 暂时单人的, 后面支持最多4人的#数据处理
+                gr.Markdown(
+                    value=i18n(
+                        "step2a: 自动遍历训练文件夹下所有可解码成音频的文件并进行切片归一化, 在实验目录下生成2个wav文件夹; 暂时只支持单人训练. "
+                    )
+                )
+                with gr.Row():
+                    trainset_dir4 = gr.Textbox(
+                        label=i18n("输入训练文件夹路径"), value="E:\\语音音频+标注\\米津玄师\\src"
+                    )
+                    spk_id5 = gr.Slider(
+                        minimum=0,
+                        maximum=4,
+                        step=1,
+                        label=i18n("请指定说话人id"),
+                        value=0,
+                        interactive=True,
+                    )
+                    but1 = gr.Button(i18n("处理数据"), variant="primary")
+                    info1 = gr.Textbox(label=i18n("输出信息"), value="")
+                    but1.click(
+                        preprocess_dataset,
+                        [trainset_dir4, exp_dir1, sr2, np7],
+                        [info1],
+                        api_name="train_preprocess",
+                    )
+            with gr.Group():
+                gr.Markdown(value=i18n("step2b: 使用CPU提取音高(如果模型带音高), 使用GPU提取特征(选择卡号)"))
+                with gr.Row():
+                    with gr.Column():
+                        gpus6 = gr.Textbox(
+                            label=i18n("以-分隔输入使用的卡号, 例如   0-1-2   使用卡0和卡1和卡2"),
+                            value=gpus,
+                            interactive=True,
+                            visible=F0GPUVisible,
+                        )
+                        gpu_info9 = gr.Textbox(
+                            label=i18n("显卡信息"), value=gpu_info, visible=F0GPUVisible
+                        )
+                    with gr.Column():
+                        f0method8 = gr.Radio(
+                            label=i18n(
+                                "选择音高提取算法:输入歌声可用pm提速,高质量语音但CPU差可用dio提速,harvest质量更好但慢,rmvpe效果最好且微吃CPU/GPU"
+                            ),
+                            choices=["pm", "harvest", "dio", "rmvpe", "rmvpe_gpu"],
+                            value="rmvpe_gpu",
+                            interactive=True,
+                        )
+                        gpus_rmvpe = gr.Textbox(
+                            label=i18n(
+                                "rmvpe卡号配置：以-分隔输入使用的不同进程卡号,例如0-0-1使用在卡0上跑2个进程并在卡1上跑1个进程"
+                            ),
+                            value="%s-%s" % (gpus, gpus),
+                            interactive=True,
+                            visible=F0GPUVisible,
+                        )
+                    but2 = gr.Button(i18n("特征提取"), variant="primary")
+                    info2 = gr.Textbox(label=i18n("输出信息"), value="", max_lines=8)
+                    f0method8.change(
+                        fn=change_f0_method,
+                        inputs=[f0method8],
+                        outputs=[gpus_rmvpe],
+                    )
+                    but2.click(
+                        extract_f0_feature,
+                        [
+                            gpus6,
+                            np7,
+                            f0method8,
+                            if_f0_3,
+                            exp_dir1,
+                            version19,
+                            gpus_rmvpe,
+                        ],
+                        [info2],
+                        api_name="train_extract_f0_feature",
+                    )
+            with gr.Group():
+                gr.Markdown(value=i18n("step3: 填写训练设置, 开始训练模型和索引"))
+                with gr.Row():
+                    save_epoch10 = gr.Slider(
+                        minimum=1,
+                        maximum=50,
+                        step=1,
+                        label=i18n("保存频率save_every_epoch"),
+                        value=5,
+                        interactive=True,
+                    )
+                    total_epoch11 = gr.Slider(
+                        minimum=2,
+                        maximum=1000,
+                        step=1,
+                        label=i18n("总训练轮数total_epoch"),
+                        value=20,
+                        interactive=True,
+                    )
+                    batch_size12 = gr.Slider(
+                        minimum=1,
+                        maximum=40,
+                        step=1,
+                        label=i18n("每张显卡的batch_size"),
+                        value=default_batch_size,
+                        interactive=True,
+                    )
+                    if_save_latest13 = gr.Radio(
+                        label=i18n("是否仅保存最新的ckpt文件以节省硬盘空间"),
+                        choices=[i18n("是"), i18n("否")],
+                        value=i18n("否"),
+                        interactive=True,
+                    )
+                    if_cache_gpu17 = gr.Radio(
+                        label=i18n(
+                            "是否缓存所有训练集至显存. 10min以下小数据可缓存以加速训练, 大数据缓存会炸显存也加不了多少速"
+                        ),
+                        choices=[i18n("是"), i18n("否")],
+                        value=i18n("否"),
+                        interactive=True,
+                    )
+                    if_save_every_weights18 = gr.Radio(
+                        label=i18n("是否在每次保存时间点将最终小模型保存至weights文件夹"),
+                        choices=[i18n("是"), i18n("否")],
+                        value=i18n("否"),
+                        interactive=True,
+                    )
+                with gr.Row():
+                    pretrained_G14 = gr.Textbox(
+                        label=i18n("加载预训练底模G路径"),
+                        value="assets/pretrained_v2/f0G40k.pth",
+                        interactive=True,
+                    )
+                    pretrained_D15 = gr.Textbox(
+                        label=i18n("加载预训练底模D路径"),
+                        value="assets/pretrained_v2/f0D40k.pth",
+                        interactive=True,
+                    )
+                    sr2.change(
+                        change_sr2,
+                        [sr2, if_f0_3, version19],
+                        [pretrained_G14, pretrained_D15],
+                    )
+                    version19.change(
+                        change_version19,
+                        [sr2, if_f0_3, version19],
+                        [pretrained_G14, pretrained_D15, sr2],
+                    )
+                    if_f0_3.change(
+                        change_f0,
+                        [if_f0_3, sr2, version19],
+                        [f0method8, pretrained_G14, pretrained_D15],
+                    )
+                    gpus16 = gr.Textbox(
+                        label=i18n("以-分隔输入使用的卡号, 例如   0-1-2   使用卡0和卡1和卡2"),
+                        value=gpus,
+                        interactive=True,
+                    )
+                    but3 = gr.Button(i18n("训练模型"), variant="primary")
+                    but4 = gr.Button(i18n("训练特征索引"), variant="primary")
+                    but5 = gr.Button(i18n("一键训练"), variant="primary")
+                    info3 = gr.Textbox(label=i18n("输出信息"), value="", max_lines=10)
+                    but3.click(
+                        click_train,
+                        [
+                            exp_dir1,
+                            sr2,
+                            if_f0_3,
+                            spk_id5,
+                            save_epoch10,
+                            total_epoch11,
+                            batch_size12,
+                            if_save_latest13,
+                            pretrained_G14,
+                            pretrained_D15,
+                            gpus16,
+                            if_cache_gpu17,
+                            if_save_every_weights18,
+                            version19,
+                        ],
+                        info3,
+                        api_name="train_start",
+                    )
+                    but4.click(train_index, [exp_dir1, version19], info3)
+                    but5.click(
+                        train1key,
+                        [
+                            exp_dir1,
+                            sr2,
+                            if_f0_3,
+                            trainset_dir4,
+                            spk_id5,
+                            np7,
+                            f0method8,
+                            save_epoch10,
+                            total_epoch11,
+                            batch_size12,
+                            if_save_latest13,
+                            pretrained_G14,
+                            pretrained_D15,
+                            gpus16,
+                            if_cache_gpu17,
+                            if_save_every_weights18,
+                            version19,
+                            gpus_rmvpe,
+                        ],
+                        info3,
+                        api_name="train_start_all",
+                    )
+
+        with gr.TabItem(i18n("ckpt处理")):
+            with gr.Group():
+                gr.Markdown(value=i18n("模型融合, 可用于测试音色融合"))
+                with gr.Row():
+                    ckpt_a = gr.Textbox(label=i18n("A模型路径"), value="", interactive=True)
+                    ckpt_b = gr.Textbox(label=i18n("B模型路径"), value="", interactive=True)
+                    alpha_a = gr.Slider(
+                        minimum=0,
+                        maximum=1,
+                        label=i18n("A模型权重"),
+                        value=0.5,
+                        interactive=True,
+                    )
+                with gr.Row():
+                    sr_ = gr.Radio(
+                        label=i18n("目标采样率"),
+                        choices=["40k", "48k"],
+                        value="40k",
+                        interactive=True,
+                    )
+                    if_f0_ = gr.Radio(
+                        label=i18n("模型是否带音高指导"),
+                        choices=[i18n("是"), i18n("否")],
+                        value=i18n("是"),
+                        interactive=True,
+                    )
+                    info__ = gr.Textbox(
+                        label=i18n("要置入的模型信息"), value="", max_lines=8, interactive=True
+                    )
+                    name_to_save0 = gr.Textbox(
+                        label=i18n("保存的模型名不带后缀"),
+                        value="",
+                        max_lines=1,
+                        interactive=True,
+                    )
+                    version_2 = gr.Radio(
+                        label=i18n("模型版本型号"),
+                        choices=["v1", "v2"],
+                        value="v1",
+                        interactive=True,
+                    )
+                with gr.Row():
+                    but6 = gr.Button(i18n("融合"), variant="primary")
+                    info4 = gr.Textbox(label=i18n("输出信息"), value="", max_lines=8)
+                but6.click(
+                    merge,
+                    [
+                        ckpt_a,
+                        ckpt_b,
+                        alpha_a,
+                        sr_,
+                        if_f0_,
+                        info__,
+                        name_to_save0,
+                        version_2,
+                    ],
+                    info4,
+                    api_name="ckpt_merge",
+                )  # def merge(path1,path2,alpha1,sr,f0,info):
+            with gr.Group():
+                gr.Markdown(value=i18n("修改模型信息(仅支持weights文件夹下提取的小模型文件)"))
+                with gr.Row():
+                    ckpt_path0 = gr.Textbox(
+                        label=i18n("模型路径"), value="", interactive=True
+                    )
+                    info_ = gr.Textbox(
+                        label=i18n("要改的模型信息"), value="", max_lines=8, interactive=True
+                    )
+                    name_to_save1 = gr.Textbox(
+                        label=i18n("保存的文件名, 默认空为和源文件同名"),
+                        value="",
+                        max_lines=8,
+                        interactive=True,
+                    )
+                with gr.Row():
+                    but7 = gr.Button(i18n("修改"), variant="primary")
+                    info5 = gr.Textbox(label=i18n("输出信息"), value="", max_lines=8)
+                but7.click(
+                    change_info,
+                    [ckpt_path0, info_, name_to_save1],
+                    info5,
+                    api_name="ckpt_modify",
+                )
+            with gr.Group():
+                gr.Markdown(value=i18n("查看模型信息(仅支持weights文件夹下提取的小模型文件)"))
+                with gr.Row():
+                    ckpt_path1 = gr.Textbox(
+                        label=i18n("模型路径"), value="", interactive=True
+                    )
+                    but8 = gr.Button(i18n("查看"), variant="primary")
+                    info6 = gr.Textbox(label=i18n("输出信息"), value="", max_lines=8)
+                but8.click(show_info, [ckpt_path1], info6, api_name="ckpt_show")
+            with gr.Group():
+                gr.Markdown(
+                    value=i18n(
+                        "模型提取(输入logs文件夹下大文件模型路径),适用于训一半不想训了模型没有自动提取保存小文件模型,或者想测试中间模型的情况"
+                    )
+                )
+                with gr.Row():
+                    ckpt_path2 = gr.Textbox(
+                        label=i18n("模型路径"),
+                        value="E:\\codes\\py39\\logs\\mi-test_f0_48k\\G_23333.pth",
+                        interactive=True,
+                    )
+                    save_name = gr.Textbox(
+                        label=i18n("保存名"), value="", interactive=True
+                    )
+                    sr__ = gr.Radio(
+                        label=i18n("目标采样率"),
+                        choices=["32k", "40k", "48k"],
+                        value="40k",
+                        interactive=True,
+                    )
+                    if_f0__ = gr.Radio(
+                        label=i18n("模型是否带音高指导,1是0否"),
+                        choices=["1", "0"],
+                        value="1",
+                        interactive=True,
+                    )
+                    version_1 = gr.Radio(
+                        label=i18n("模型版本型号"),
+                        choices=["v1", "v2"],
+                        value="v2",
+                        interactive=True,
+                    )
+                    info___ = gr.Textbox(
+                        label=i18n("要置入的模型信息"), value="", max_lines=8, interactive=True
+                    )
+                    but9 = gr.Button(i18n("提取"), variant="primary")
+                    info7 = gr.Textbox(label=i18n("输出信息"), value="", max_lines=8)
+                    ckpt_path2.change(
+                        change_info_, [ckpt_path2], [sr__, if_f0__, version_1]
+                    )
+                but9.click(
+                    extract_small_model,
+                    [ckpt_path2, save_name, sr__, if_f0__, info___, version_1],
+                    info7,
+                    api_name="ckpt_extract",
+                )
+
+        with gr.TabItem(i18n("Onnx导出")):
+            with gr.Row():
+                ckpt_dir = gr.Textbox(label=i18n("RVC模型路径"), value="", interactive=True)
+            with gr.Row():
+                onnx_dir = gr.Textbox(
+                    label=i18n("Onnx输出路径"), value="", interactive=True
+                )
+            with gr.Row():
+                infoOnnx = gr.Label(label="info")
+            with gr.Row():
+                butOnnx = gr.Button(i18n("导出Onnx模型"), variant="primary")
+            butOnnx.click(
+                export_onnx, [ckpt_dir, onnx_dir], infoOnnx, api_name="export_onnx"
+            )
+
+        tab_faq = i18n("常见问题解答")
+        with gr.TabItem(tab_faq):
+            try:
+                if tab_faq == "常见问题解答":
+                    with open("docs/cn/faq.md", "r", encoding="utf8") as f:
+                        info = f.read()
+                else:
+                    with open("docs/en/faq_en.md", "r", encoding="utf8") as f:
+                        info = f.read()
+                gr.Markdown(value=info)
+            except:
+                gr.Markdown(traceback.format_exc())
+
+    if config.iscolab:
+        app.queue(concurrency_count=511, max_size=1022).launch(share=True)
+    else:
+        app.queue(concurrency_count=511, max_size=1022).launch(
+            server_name="0.0.0.0",
+            inbrowser=not config.noautoopen,
+            server_port=config.listen_port,
+            quiet=True,
+        )

pyproject.toml

@@ -0,0 +1,63 @@
+[tool.poetry]
+name = "rvc-beta"
+version = "0.1.0"
+description = ""
+authors = ["lj1995"]
+license = "MIT"
+
+[tool.poetry.dependencies]
+python = "^3.8"
+torch = "^2.0.0"
+torchaudio = "^2.0.1"
+Cython = "^0.29.34"
+gradio = "^3.34.0"
+future = "^0.18.3"
+pydub = "^0.25.1"
+soundfile = "^0.12.1"
+ffmpeg-python = "^0.2.0"
+tensorboardX = "^2.6"
+functorch = "^2.0.0"
+fairseq = "^0.12.2"
+faiss-cpu = "^1.7.2"
+Jinja2 = "^3.1.2"
+json5 = "^0.9.11"
+librosa = "0.9.1"
+llvmlite = "0.39.0"
+Markdown = "^3.4.3"
+matplotlib = "^3.7.1"
+matplotlib-inline = "^0.1.6"
+numba = "0.56.4"
+numpy = "1.23.5"
+scipy = "1.9.3"
+praat-parselmouth = "^0.4.3"
+Pillow = "9.3.0"
+pyworld = "^0.3.2"
+resampy = "^0.4.2"
+scikit-learn = "^1.2.2"
+starlette = "^0.27.0"
+tensorboard = "^2.12.1"
+tensorboard-data-server = "^0.7.0"
+tensorboard-plugin-wit = "^1.8.1"
+torchgen = "^0.0.1"
+tqdm = "^4.65.0"
+tornado = "^6.3"
+Werkzeug = "^2.2.3"
+uc-micro-py = "^1.0.1"
+sympy = "^1.11.1"
+tabulate = "^0.9.0"
+PyYAML = "^6.0"
+pyasn1 = "^0.4.8"
+pyasn1-modules = "^0.2.8"
+fsspec = "^2023.3.0"
+absl-py = "^1.4.0"
+audioread = "^3.0.0"
+uvicorn = "^0.21.1"
+colorama = "^0.4.6"
+torchcrepe = "0.0.20"
+python-dotenv = "^1.0.0"
+
+[tool.poetry.dev-dependencies]
+
+[build-system]
+requires = ["poetry-core>=1.0.0"]
+build-backend = "poetry.core.masonry.api"

requirements-dml.txt

@@ -0,0 +1,48 @@
+gdown
+mega.py
+joblib>=1.1.0
+numba==0.56.4
+numpy==1.23.5
+scipy
+librosa==0.9.1
+llvmlite==0.39.0
+fairseq==0.12.2
+faiss-cpu==1.7.3
+gradio==3.34.0
+Cython
+pydub>=0.25.1
+soundfile>=0.12.1
+ffmpeg-python>=0.2.0
+tensorboardX
+Jinja2>=3.1.2
+json5
+Markdown
+matplotlib>=3.7.0
+matplotlib-inline>=0.1.3
+praat-parselmouth>=0.4.2
+Pillow>=9.1.1
+resampy>=0.4.2
+scikit-learn
+tensorboard
+tqdm>=4.63.1
+tornado>=6.1
+Werkzeug>=2.2.3
+uc-micro-py>=1.0.1
+sympy>=1.11.1
+tabulate>=0.8.10
+PyYAML>=6.0
+pyasn1>=0.4.8
+pyasn1-modules>=0.2.8
+fsspec>=2022.11.0
+absl-py>=1.2.0
+audioread
+uvicorn>=0.21.1
+colorama>=0.4.5
+pyworld==0.3.2
+httpx
+onnxruntime-directml
+torchcrepe==0.0.20
+fastapi==0.88
+ffmpy==0.3.1
+python-dotenv>=1.0.0
+av

requirements-ipex.txt

@@ -0,0 +1,54 @@
+torch==2.0.1a0
+intel_extension_for_pytorch==2.0.110+xpu
+torchvision==0.15.2a0
+https://github.com/Disty0/Retrieval-based-Voice-Conversion-WebUI/releases/download/torchaudio_wheels_for_ipex/torchaudio-2.0.2+31de77d-cp310-cp310-linux_x86_64.whl
+-f https://developer.intel.com/ipex-whl-stable-xpu
+joblib>=1.1.0
+numba==0.56.4
+numpy==1.23.5
+scipy
+librosa==0.9.1
+llvmlite==0.39.0
+fairseq==0.12.2
+faiss-cpu==1.7.3
+gradio==3.34.0
+Cython
+pydub>=0.25.1
+soundfile>=0.12.1
+ffmpeg-python>=0.2.0
+tensorboardX
+Jinja2>=3.1.2
+json5
+Markdown
+matplotlib>=3.7.0
+matplotlib-inline>=0.1.3
+praat-parselmouth>=0.4.2
+Pillow>=9.1.1
+resampy>=0.4.2
+scikit-learn
+tensorboard
+tqdm>=4.63.1
+tornado>=6.1
+Werkzeug>=2.2.3
+uc-micro-py>=1.0.1
+sympy>=1.11.1
+tabulate>=0.8.10
+PyYAML>=6.0
+pyasn1>=0.4.8
+pyasn1-modules>=0.2.8
+fsspec>=2022.11.0
+absl-py>=1.2.0
+audioread
+uvicorn>=0.21.1
+colorama>=0.4.5
+pyworld==0.3.2
+httpx
+onnxruntime; sys_platform == 'darwin'
+onnxruntime-gpu; sys_platform != 'darwin'
+torchcrepe==0.0.20
+fastapi==0.88
+ffmpy==0.3.1
+python-dotenv>=1.0.0
+av
+PySimpleGUI
+sounddevice

requirements-safe.txt

@@ -0,0 +1,52 @@
+torch
+torchvision
+torchaudio
+gdown
+mega.py
+joblib>=1.1.0
+numba==0.56.4
+numpy==1.22.0
+scipy
+librosa==0.9.1
+llvmlite==0.39.0
+fairseq==0.12.2
+faiss-cpu==1.7.3
+Cython
+pydub>=0.25.1
+soundfile>=0.12.1
+ffmpeg-python>=0.2.0
+tensorboardX
+Jinja2>=3.1.2
+json5
+Markdown
+matplotlib>=3.7.0
+matplotlib-inline>=0.1.3
+praat-parselmouth>=0.4.2
+Pillow>=9.1.1
+resampy>=0.4.2
+scikit-learn
+tensorboard
+tqdm>=4.63.1
+tornado>=6.1
+Werkzeug>=2.2.3
+uc-micro-py>=1.0.1
+sympy>=1.11.1
+tabulate>=0.8.10
+PyYAML>=6.0
+pyasn1>=0.4.8
+pyasn1-modules>=0.2.8
+fsspec>=2022.11.0
+absl-py>=1.2.0
+audioread
+uvicorn>=0.21.1
+colorama>=0.4.5
+pyworld==0.3.2
+httpx
+onnxruntime; sys_platform == 'darwin'
+onnxruntime-gpu; sys_platform != 'darwin'
+torchcrepe==0.0.20
+fastapi==0.88
+ffmpy==0.3.1
+python-dotenv>=1.0.0
+av
+pydantic==1.10.12

requirements-win-for-realtime_vc_gui-dml.txt

@@ -0,0 +1,29 @@
+#1.Install torch from pytorch.org:
+#torch 2.0 with cuda 11.8
+#pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
+#torch 1.11.0 with cuda 11.3
+#pip install torch==1.11.0+cu113 torchvision==0.12.0+cu113 torchaudio==0.11.0 --extra-index-url https://download.pytorch.org/whl/cu113
+einops
+fairseq
+flask
+flask_cors
+gin
+gin_config
+librosa
+local_attention
+matplotlib
+praat-parselmouth
+pyworld
+PyYAML
+resampy
+scikit_learn
+scipy
+SoundFile
+tensorboard
+tqdm
+wave
+PySimpleGUI
+sounddevice
+gradio
+noisereduce
+onnxruntime-directml

requirements-win-for-realtime_vc_gui.txt

@@ -0,0 +1,28 @@
+#1.Install torch from pytorch.org:
+#torch 2.0 with cuda 11.8
+#pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
+#torch 1.11.0 with cuda 11.3
+#pip install torch==1.11.0+cu113 torchvision==0.12.0+cu113 torchaudio==0.11.0 --extra-index-url https://download.pytorch.org/whl/cu113
+einops
+fairseq
+flask
+flask_cors
+gin
+gin_config
+librosa
+local_attention
+matplotlib
+praat-parselmouth
+pyworld
+PyYAML
+resampy
+scikit_learn
+scipy
+SoundFile
+tensorboard
+tqdm
+wave
+PySimpleGUI
+sounddevice
+gradio
+noisereduce

requirements.txt

@@ -0,0 +1,53 @@
+torch
+torchvision
+torchaudio
+gdown
+mega.py
+joblib>=1.1.0
+numba==0.56.4
+numpy==1.22.0
+scipy
+librosa==0.9.1
+llvmlite==0.39.0
+fairseq==0.12.2
+faiss-cpu==1.7.3
+gradio==3.43.2
+Cython
+pydub>=0.25.1
+soundfile>=0.12.1
+ffmpeg-python>=0.2.0
+tensorboardX
+Jinja2>=3.1.2
+json5
+Markdown
+matplotlib>=3.7.0
+matplotlib-inline>=0.1.3
+praat-parselmouth>=0.4.2
+Pillow>=9.1.1
+resampy>=0.4.2
+scikit-learn
+tensorboard
+tqdm>=4.63.1
+tornado>=6.1
+Werkzeug>=2.2.3
+uc-micro-py>=1.0.1
+sympy>=1.11.1
+tabulate>=0.8.10
+PyYAML>=6.0
+pyasn1>=0.4.8
+pyasn1-modules>=0.2.8
+fsspec>=2022.11.0
+absl-py>=1.2.0
+audioread
+uvicorn>=0.21.1
+colorama>=0.4.5
+pyworld==0.3.2
+httpx
+onnxruntime; sys_platform == 'darwin'
+onnxruntime-gpu; sys_platform != 'darwin'
+torchcrepe==0.0.20
+fastapi==0.88
+ffmpy==0.3.1
+python-dotenv>=1.0.0
+av
+pydantic==1.10.12

run.sh

@@ -0,0 +1,61 @@
+#!/bin/bash
+
+if [[ "$(uname)" == "Darwin" ]]; then
+  # macOS specific env:
+  export PYTORCH_ENABLE_MPS_FALLBACK=1
+  export PYTORCH_MPS_HIGH_WATERMARK_RATIO=0.0
+elif [[ "$(uname)" != "Linux" ]]; then
+  echo "Unsupported operating system."
+  exit 1
+fi
+
+if [ -d ".venv" ]; then
+  echo "Activate venv..."
+  source .venv/bin/activate
+else
+  echo "Create venv..."
+  requirements_file="requirements.txt"
+
+  # Check if Python 3.8 is installed
+  if ! command -v python3 &> /dev/null; then
+    echo "Python 3 not found. Attempting to install 3.8..."
+    if [[ "$(uname)" == "Darwin" ]] && command -v brew &> /dev/null; then
+      brew install [email protected]
+    elif [[ "$(uname)" == "Linux" ]] && command -v apt-get &> /dev/null; then
+      sudo apt-get update
+      sudo apt-get install python3.8
+    else
+      echo "Please install Python 3.8 manually."
+      exit 1
+    fi
+  fi
+
+  python3 -m venv .venv
+  source .venv/bin/activate
+
+  # Check if required packages are installed and install them if not
+  if [ -f "${requirements_file}" ]; then
+    installed_packages=$(python3 -m pip freeze)
+    while IFS= read -r package; do
+      [[ "${package}" =~ ^#.* ]] && continue
+      package_name=$(echo "${package}" | sed 's/[<>=!].*//')
+      if ! echo "${installed_packages}" | grep -q "${package_name}"; then
+        echo "${package_name} not found. Attempting to install..."
+        python3 -m pip install --upgrade "${package}"
+      fi
+    done < "${requirements_file}"
+  else
+    echo "${requirements_file} not found. Please ensure the requirements file with required packages exists."
+    exit 1
+  fi
+fi
+
+# Download models
+./tools/dlmodels.sh
+
+if [[ $? -ne 0 ]]; then
+  exit 1
+fi
+
+# Run the main script
+python3 infer-web.py --pycmd python3

venv.sh

@@ -0,0 +1 @@
+python3.8 -m venv .venv