Upload 4 files

tools/xiaoshuang/G_10000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2335a53da1b3e984d0e3a99bf8b2dd86482bd368dc8bf9311cbba448d3596e9c
+size 728379397

tools/xiaoshuang/G_8000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4fccb4ebdb53370c8520dec1c78c2d770d540ef59f287b665b368f9ecf6fbdc
+size 728369839

tools/xiaoshuang/config.json

@@ -0,0 +1,108 @@
+{
+  "train": {
+    "log_interval": 200,
+    "eval_interval": 1000,
+    "seed": 42,
+    "epochs": 1000,
+    "learning_rate": 0.0002,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 16,
+    "bf16_run": false,
+    "lr_decay": 0.99995,
+    "segment_size": 16384,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0,
+    "c_commit": 100,
+    "skip_optimizer": true,
+    "freeze_ZH_bert": false,
+    "freeze_JP_bert": false,
+    "freeze_EN_bert": false,
+    "freeze_emo": false
+  },
+  "data": {
+    "training_files": "filelists/train.list",
+    "validation_files": "filelists/val.list",
+    "max_wav_value": 32768.0,
+    "sampling_rate": 44100,
+    "filter_length": 2048,
+    "hop_length": 512,
+    "win_length": 2048,
+    "n_mel_channels": 128,
+    "mel_fmin": 0.0,
+    "mel_fmax": null,
+    "add_blank": true,
+    "n_speakers": 1,
+    "cleaned_text": true,
+    "spk2id": {
+      "shuang": 0
+    }
+  },
+  "model": {
+    "use_spk_conditioned_encoder": true,
+    "use_noise_scaled_mas": true,
+    "use_mel_posterior_encoder": false,
+    "use_duration_discriminator": true,
+    "inter_channels": 192,
+    "hidden_channels": 192,
+    "filter_channels": 768,
+    "n_heads": 2,
+    "n_layers": 6,
+    "kernel_size": 3,
+    "p_dropout": 0.1,
+    "resblock": "1",
+    "resblock_kernel_sizes": [
+      3,
+      7,
+      11
+    ],
+    "resblock_dilation_sizes": [
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ]
+    ],
+    "upsample_rates": [
+      8,
+      8,
+      2,
+      2,
+      2
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      8,
+      2,
+      2
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 512,
+    "slm": {
+      "model": "./slm/wavlm-base-plus",
+      "sr": 16000,
+      "hidden": 768,
+      "nlayers": 13,
+      "initial_channel": 64
+    }
+  },
+  "version": "2.3"
+}

tools/xiaoshuang/config.yml

@@ -0,0 +1,62 @@
+bert_gen:
+  config_path: config.json
+  device: cuda
+  num_processes: 4
+  use_multi_device: false
+dataset_path: Data\xiaoshuang
+emo_gen:
+  config_path: config.json
+  device: cuda
+  num_processes: 4
+  use_multi_device: false
+mirror: ''
+openi_token: ''
+preprocess_text:
+  clean: true
+  cleaned_path: filelists/cleaned.list
+  config_path: config.json
+  max_val_total: 12
+  train_path: filelists/train.list
+  transcription_path: filelists/short_character_anno.list
+  val_path: filelists/val.list
+  val_per_lang: 4
+resample:
+  in_dir: raw
+  out_dir: wavs
+  sampling_rate: 44100
+server:
+  device: cuda
+  models:
+  - config: Data\xiaoshuang\config.json
+    device: cuda
+    language: ZH
+    model: Data\xiaoshuang\models\G_8000.pth
+    speakers: []
+  port: 5000
+train_ms:
+  base:
+    model_image: "Bert-VITS2_2.3\u5E95\u6A21"
+    repo_id: Stardust_minus/Bert-VITS2
+    use_base_model: false
+  config_path: config.json
+  env:
+    LOCAL_RANK: 0
+    MASTER_ADDR: localhost
+    MASTER_PORT: 10086
+    RANK: 0
+    WORLD_SIZE: 1
+  keep_ckpts: 10
+  model: models
+  num_workers: 2
+  spec_cache: true
+translate:
+  app_key: ''
+  secret_key: ''
+webui:
+  config_path: config.json
+  debug: false
+  device: cuda
+  language_identification_library: langid
+  model: models/G_8000.pth
+  port: 7860
+  share: true