Upload 6 files

whisper1_null/config.json

@@ -0,0 +1,87 @@
+{
+  "model_name": "whisper1_null",
+  "train": {
+    "log_interval": 200,
+    "eval_interval": 1000,
+    "seed": 42,
+    "epochs": 100,
+    "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": false,
+    "freeze_ZH_bert": false,
+    "freeze_JP_bert": false,
+    "freeze_EN_bert": false,
+    "freeze_emo": false,
+    "freeze_style": false,
+    "freeze_decoder": false
+  },
+  "data": {
+    "use_jp_extra": true,
+    "training_files": "Data\\Dummy\\train.list",
+    "validation_files": "Data\\Dummy\\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": {
+      "Dummy": 0
+    },
+    "num_styles": 1,
+    "style2id": {
+      "Neutral": 0
+    }
+  },
+  "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": "2.5.0-JP-Extra"
+}

whisper1_null/style_vectors.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bebad3d89a0b32f0497370339ec5efb1a9058eb748f06bad7854ef0e418dab6d
+size 1152

whisper1_null/whisper1_null.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed8ce605ab8e619186665d98a03635ea479b83639edb1b1e0b7adc3cde7212ef
+size 251150980

whisper2_null/config.json

@@ -0,0 +1,87 @@
+{
+  "model_name": "whisper2_null",
+  "train": {
+    "log_interval": 200,
+    "eval_interval": 1000,
+    "seed": 42,
+    "epochs": 100,
+    "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": false,
+    "freeze_ZH_bert": false,
+    "freeze_JP_bert": false,
+    "freeze_EN_bert": false,
+    "freeze_emo": false,
+    "freeze_style": false,
+    "freeze_decoder": false
+  },
+  "data": {
+    "use_jp_extra": true,
+    "training_files": "Data\\Dummy\\train.list",
+    "validation_files": "Data\\Dummy\\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": {
+      "Dummy": 0
+    },
+    "num_styles": 1,
+    "style2id": {
+      "Neutral": 0
+    }
+  },
+  "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": "2.5.0-JP-Extra"
+}

whisper2_null/style_vectors.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e725257158fecb6ff19019e963d5d108ead25b857fd2edcef828955a125fd666
+size 1152

whisper2_null/whisper2_null.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b4aa9ca31a51a826f1030cbd8144daba3143911f82f00ac2499e1ba4831c957
+size 251150980