Delete old model_assets

model_assets/jvnv-F1/config.json

@@ -1,79 +0,0 @@
-{
-  "model_name": "jvnv-F1",
-  "train": {
-    "log_interval": 200,
-    "eval_interval": 1000,
-    "seed": 42,
-    "epochs": 500,
-    "learning_rate": 0.0002,
-    "betas": [0.8, 0.99],
-    "eps": 1e-9,
-    "batch_size": 4,
-    "bf16_run": true,
-    "lr_decay": 0.99995,
-    "segment_size": 16384,
-    "init_lr_ratio": 1,
-    "warmup_epochs": 0,
-    "c_mel": 45,
-    "c_kl": 1.0,
-    "skip_optimizer": false,
-    "freeze_ZH_bert": false,
-    "freeze_JP_bert": false,
-    "freeze_EN_bert": false
-  },
-  "data": {
-    "training_files": "Data/jvnv-F1/train.list",
-    "validation_files": "Data/jvnv-F1/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,
-    "num_styles": 7,
-    "style2id": {
-      "Neutral": 0,
-      "Angry": 1,
-      "Disgust": 2,
-      "Fear": 3,
-      "Happy": 4,
-      "Sad": 5,
-      "Surprise": 6
-    },
-    "spk2id": {
-      "jvnv-F1": 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": 256
-  },
-  "version": "1.0"
-}

model_assets/jvnv-F1/jvnv-F1.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:62c45494f0222888f9e8834ba3ccdc7cb53024e67b6f9903ceff4c011d44630c
-size 198768188

model_assets/jvnv-F1/style_vectors.npy

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

model_assets/jvnv-F2/config.json

@@ -1,79 +0,0 @@
-{
-  "model_name": "jvnv-F2",
-  "train": {
-    "log_interval": 200,
-    "eval_interval": 1000,
-    "seed": 42,
-    "epochs": 500,
-    "learning_rate": 0.0002,
-    "betas": [0.8, 0.99],
-    "eps": 1e-9,
-    "batch_size": 4,
-    "bf16_run": true,
-    "lr_decay": 0.99995,
-    "segment_size": 16384,
-    "init_lr_ratio": 1,
-    "warmup_epochs": 0,
-    "c_mel": 45,
-    "c_kl": 1.0,
-    "skip_optimizer": false,
-    "freeze_ZH_bert": false,
-    "freeze_JP_bert": false,
-    "freeze_EN_bert": false
-  },
-  "data": {
-    "training_files": "Data/jvnv-F2/train.list",
-    "validation_files": "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,
-    "num_styles": 7,
-    "style2id": {
-      "Neutral": 0,
-      "Angry": 1,
-      "Disgust": 2,
-      "Fear": 3,
-      "Happy": 4,
-      "Sad": 5,
-      "Surprise": 6
-    },
-    "spk2id": {
-      "jvnv-F2": 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": 256
-  },
-  "version": "1.0"
-}

model_assets/jvnv-F2/jvnv-F2.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7408a75ec677d461a8e959d3f2fed5256deaa8691fd841672e0a368007f9b682
-size 198768188

model_assets/jvnv-F2/style_vectors.npy

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

model_assets/jvnv-M1/config.json

@@ -1,79 +0,0 @@
-{
-  "model_name": "jvnv-M1",
-  "train": {
-    "log_interval": 200,
-    "eval_interval": 1000,
-    "seed": 42,
-    "epochs": 500,
-    "learning_rate": 0.0002,
-    "betas": [0.8, 0.99],
-    "eps": 1e-9,
-    "batch_size": 4,
-    "bf16_run": true,
-    "lr_decay": 0.99995,
-    "segment_size": 16384,
-    "init_lr_ratio": 1,
-    "warmup_epochs": 0,
-    "c_mel": 45,
-    "c_kl": 1.0,
-    "skip_optimizer": false,
-    "freeze_ZH_bert": false,
-    "freeze_JP_bert": false,
-    "freeze_EN_bert": false
-  },
-  "data": {
-    "training_files": "Data/jvnv-M1/train.list",
-    "validation_files": "Data/jvnv-M1/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,
-    "num_styles": 7,
-    "style2id": {
-      "Neutral": 0,
-      "Angry": 1,
-      "Disgust": 2,
-      "Fear": 3,
-      "Happy": 4,
-      "Sad": 5,
-      "Surprise": 6
-    },
-    "spk2id": {
-      "jvnv-M1": 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": 256
-  },
-  "version": "1.2"
-}

model_assets/jvnv-M1/jvnv-M1.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:397cc7e0b8ea1e290a7049802c2894315381ad84657947779078f79a36e98729
-size 198768188

model_assets/jvnv-M1/style_vectors.npy

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

model_assets/jvnv-M2/config.json

@@ -1,79 +0,0 @@
-{
-  "model_name": "jvnv-M2",
-  "train": {
-    "log_interval": 200,
-    "eval_interval": 1000,
-    "seed": 42,
-    "epochs": 300,
-    "learning_rate": 0.0002,
-    "betas": [0.8, 0.99],
-    "eps": 1e-9,
-    "batch_size": 4,
-    "bf16_run": true,
-    "lr_decay": 0.99995,
-    "segment_size": 16384,
-    "init_lr_ratio": 1,
-    "warmup_epochs": 0,
-    "c_mel": 45,
-    "c_kl": 1.0,
-    "skip_optimizer": false,
-    "freeze_ZH_bert": false,
-    "freeze_JP_bert": false,
-    "freeze_EN_bert": false
-  },
-  "data": {
-    "training_files": "Data/jvnv-M2/train.list",
-    "validation_files": "Data/jvnv-M2/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,
-    "num_styles": 7,
-    "style2id": {
-      "Neutral": 0,
-      "Angry": 1,
-      "Disgust": 2,
-      "Fear": 3,
-      "Happy": 4,
-      "Sad": 5,
-      "Surprise": 6
-    },
-    "spk2id": {
-      "jvnv-M2": 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": 256
-  },
-  "version": "1.2"
-}

model_assets/jvnv-M2/jvnv-M2.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2fcc35ddfddc94234c5d3f30d3c5c865c66b0ba2ad12ed2a13afd2c4878119e2
-size 198768188

model_assets/jvnv-M2/style_vectors.npy

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