Upload 14 files

model_assets/jvnv-F1-jp/config.json

@@ -0,0 +1,92 @@
+{
+ "train": {
+ "log_interval": 200,
+ "eval_interval": 1000,
+ "seed": 42,
+ "epochs": 300,
+ "learning_rate": 0.0001,
+ "betas": [0.8, 0.99],
+ "eps": 1e-9,
+ "batch_size": 4,
+ "bf16_run": true,
+ "fp16_run": false,
+ "lr_decay": 0.99996,
+ "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,
+ "freeze_style": false
+ },
+ "data": {
+ "use_jp_extra": true,
+ "training_files": "Data/jvnv-F1-jp/train.list",
+ "validation_files": "Data/jvnv-F1-jp/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": {
+ "jvnv-F1-jp": 0
+ },
+ "num_styles": 7,
+ "style2id": {
+ "Neutral": 0,
+ "Angry": 1,
+ "Disgust": 2,
+ "Fear": 3,
+ "Happy": 4,
+ "Sad": 5,
+ "Surprise": 6
+ }
+ },
+ "model": {
+ "use_spk_conditioned_encoder": true,
+ "use_noise_scaled_mas": true,
+ "use_mel_posterior_encoder": false,
+ "use_duration_discriminator": false,
+ "use_wavlm_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": "2.0-JP-Extra",
+ "model_name": "jvnv-F1-jp"
+}

model_assets/jvnv-F1-jp/jvnv-F1-jp_e182_s16000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd324b2dd04b4a3384e0dbf4a268fd8a9bbedcfe80608fbd2a3aaaa44e474abe
+size 251150980

model_assets/jvnv-F1-jp/style_vectors.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f959bb45ed0922efc31ff24e9147253814f42cb1d2d1e2bb10391a9df368489
+size 7296

model_assets/jvnv-F2-jp/config.json

@@ -0,0 +1,92 @@
+{
+ "train": {
+ "log_interval": 200,
+ "eval_interval": 1000,
+ "seed": 42,
+ "epochs": 300,
+ "learning_rate": 0.0001,
+ "betas": [0.8, 0.99],
+ "eps": 1e-9,
+ "batch_size": 4,
+ "bf16_run": false,
+ "fp16_run": false,
+ "lr_decay": 0.99996,
+ "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,
+ "freeze_style": false
+ },
+ "data": {
+ "use_jp_extra": true,
+ "training_files": "/content/drive/MyDrive/Style-Bert-VITS2/Data/jvnv-F2/train.list",
+ "validation_files": "/content/drive/MyDrive/Style-Bert-VITS2/Data/jvnv-F2/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": {
+ "jvnv-F2-jp": 0
+ },
+ "num_styles": 7,
+ "style2id": {
+ "Neutral": 0,
+ "Angry": 1,
+ "Disgust": 2,
+ "Fear": 3,
+ "Happy": 4,
+ "Sad": 5,
+ "Surprise": 6
+ }
+ },
+ "model": {
+ "use_spk_conditioned_encoder": true,
+ "use_noise_scaled_mas": true,
+ "use_mel_posterior_encoder": false,
+ "use_duration_discriminator": false,
+ "use_wavlm_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": "2.0-JP-Extra",
+ "model_name": "jvnv-F2-jp"
+}

model_assets/jvnv-F2-jp/jvnv-F2_e166_s20000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6289a6f30bb9795744815b9da764a3c8198b18652d9fddef82fff1e14f0e784
+size 251150980

model_assets/jvnv-F2-jp/style_vectors.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:900f8cde3a336d12193fec7b7d8e6c5dc77b3a5d719a9be3f8598389cd88e643
+size 7296

model_assets/jvnv-M1-jp/config.json

@@ -0,0 +1,92 @@
+{
+ "train": {
+ "log_interval": 200,
+ "eval_interval": 1000,
+ "seed": 42,
+ "epochs": 300,
+ "learning_rate": 0.0001,
+ "betas": [0.8, 0.99],
+ "eps": 1e-9,
+ "batch_size": 4,
+ "bf16_run": true,
+ "fp16_run": false,
+ "lr_decay": 0.99996,
+ "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,
+ "freeze_style": false
+ },
+ "data": {
+ "use_jp_extra": true,
+ "training_files": "Data/jvnv-M1-jp/train.list",
+ "validation_files": "Data/jvnv-M1-jp/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": {
+ "jvnv-M1-jp": 0
+ },
+ "num_styles": 7,
+ "style2id": {
+ "Neutral": 0,
+ "Angry": 1,
+ "Disgust": 2,
+ "Fear": 3,
+ "Happy": 4,
+ "Sad": 5,
+ "Surprise": 6
+ }
+ },
+ "model": {
+ "use_spk_conditioned_encoder": true,
+ "use_noise_scaled_mas": true,
+ "use_mel_posterior_encoder": false,
+ "use_duration_discriminator": false,
+ "use_wavlm_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": "2.0-JP-Extra",
+ "model_name": "jvnv-M1-jp"
+}

model_assets/jvnv-M1-jp/jvnv-M1-jp_e158_s14000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d86765f1fe08dbba74cd06283e96b6941b3f232329fabbba9c30e6edc27887a
+size 251150980

model_assets/jvnv-M1-jp/style_vectors.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a925435e8c1c9efc8fc8e90e690655ab9a7bae00a790892e13e936510d04f05
+size 7296

model_assets/jvnv-M2-jp/config.json

@@ -0,0 +1,92 @@
+{
+ "train": {
+ "log_interval": 200,
+ "eval_interval": 1000,
+ "seed": 42,
+ "epochs": 300,
+ "learning_rate": 0.0001,
+ "betas": [0.8, 0.99],
+ "eps": 1e-9,
+ "batch_size": 4,
+ "bf16_run": true,
+ "fp16_run": false,
+ "lr_decay": 0.99996,
+ "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,
+ "freeze_style": false
+ },
+ "data": {
+ "use_jp_extra": true,
+ "training_files": "Data/jvnv-M2-jp/train.list",
+ "validation_files": "Data/jvnv-M2-jp/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": {
+ "jvnv-M2-jp": 0
+ },
+ "num_styles": 7,
+ "style2id": {
+ "Neutral": 0,
+ "Angry": 1,
+ "Disgust": 2,
+ "Fear": 3,
+ "Happy": 4,
+ "Sad": 5,
+ "Surprise": 6
+ }
+ },
+ "model": {
+ "use_spk_conditioned_encoder": true,
+ "use_noise_scaled_mas": true,
+ "use_mel_posterior_encoder": false,
+ "use_duration_discriminator": false,
+ "use_wavlm_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": "2.0-JP-Extra",
+ "model_name": "jvnv-M2-jp"
+}

model_assets/jvnv-M2-jp/jvnv-M2-jp_e159_s17000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8245f39438076d36a3befd8aefb15c38830cef326c1f7c9d9c8e64b647645402
+size 251150980

model_assets/jvnv-M2-jp/style_vectors.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c965bb63fa4a759d41a8a4a3649333125d6497ae8a705d81b7d5c5bd2854797c
+size 7296

monotonic_align/__init__.py

@@ -0,0 +1,16 @@
+from numpy import zeros, int32, float32
+from torch import from_numpy
+
+from .core import maximum_path_jit
+
+
+def maximum_path(neg_cent, mask):
+ device = neg_cent.device
+ dtype = neg_cent.dtype
+ neg_cent = neg_cent.data.cpu().numpy().astype(float32)
+ path = zeros(neg_cent.shape, dtype=int32)
+
+ t_t_max = mask.sum(1)[:, 0].data.cpu().numpy().astype(int32)
+ t_s_max = mask.sum(2)[:, 0].data.cpu().numpy().astype(int32)
+ maximum_path_jit(path, neg_cent, t_t_max, t_s_max)
+ return from_numpy(path).to(device=device, dtype=dtype)

monotonic_align/core.py

@@ -0,0 +1,46 @@
+import numba
+
+
+@numba.jit(
+ numba.void(
+ numba.int32[:, :, ::1],
+ numba.float32[:, :, ::1],
+ numba.int32[::1],
+ numba.int32[::1],
+ ),
+ nopython=True,
+ nogil=True,
+)
+def maximum_path_jit(paths, values, t_ys, t_xs):
+ b = paths.shape[0]
+ max_neg_val = -1e9
+ for i in range(int(b)):
+ path = paths[i]
+ value = values[i]
+ t_y = t_ys[i]
+ t_x = t_xs[i]
+
+ v_prev = v_cur = 0.0
+ index = t_x - 1
+
+ for y in range(t_y):
+ for x in range(max(0, t_x + y - t_y), min(t_x, y + 1)):
+ if x == y:
+ v_cur = max_neg_val
+ else:
+ v_cur = value[y - 1, x]
+ if x == 0:
+ if y == 0:
+ v_prev = 0.0
+ else:
+ v_prev = max_neg_val
+ else:
+ v_prev = value[y - 1, x - 1]
+ value[y, x] += max(v_prev, v_cur)
+
+ for y in range(t_y - 1, -1, -1):
+ path[y, index] = 1
+ if index != 0 and (
+ index == y or value[y - 1, index] < value[y - 1, index - 1]
+ ):
+ index = index - 1