Upload folder using huggingface_hub

D_1470000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04f96aeeebb01a0117efeaad6bbd70302db7682497c5d89c8cb7addcece7403d
+size 561100090

G_1470000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:021afc97b3d0cd234b8350509d39a94f222e4151a4ee7387d74dfbe0f63fe20d
+size 474380318

config.json

@@ -0,0 +1,54 @@
+{
+  "train": {
+    "log_interval": 200,
+    "eval_interval": 10000,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 2e-4,
+    "betas": [0.8, 0.99],
+    "eps": 1e-9,
+    "batch_size": 64,
+    "fp16_run": false,
+    "lr_decay": 0.999875,
+    "segment_size": 8960,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0,
+    "use_sr": false,
+    "max_speclen": 128,
+    "port": "8001"
+  },
+  "data": {
+    "training_files":"/home/jovyan/voice-chung/stbase/vits/data/librispeech/train.txt",
+    "validation_files":"/home/jovyan/voice-chung/stbase/vits/data/librispeech/val.txt",
+    "max_wav_value": 32768.0,
+    "sampling_rate": 16000,
+    "filter_length": 1280,
+    "hop_length": 320,
+    "win_length": 1280,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": null
+  },
+  "model": {
+    "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": [10,8,2,2],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [16,16,4,4],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256,
+    "ssl_dim": 1024,
+    "use_spk": true
+  }
+}

stage1/D_450000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f0ab52e9a4b99f4a53b6522efe7e246a64209bb3c12f1e8dc38878633f434e0
+size 561099642

stage1/G_450000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed3298544b2f91cca6143181fac58a72e36f37c1148e07e393b0bb342962c22a
+size 474378062

stage1/config.json

@@ -0,0 +1,54 @@
+{
+  "train": {
+    "log_interval": 200,
+    "eval_interval": 10000,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 2e-4,
+    "betas": [0.8, 0.99],
+    "eps": 1e-9,
+    "batch_size": 64,
+    "fp16_run": false,
+    "lr_decay": 0.999875,
+    "segment_size": 8960,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0,
+    "use_sr": false,
+    "max_speclen": 128,
+    "port": "8001"
+  },
+  "data": {
+    "training_files":"filelists/train.txt",
+    "validation_files":"filelists/val.txt",
+    "max_wav_value": 32768.0,
+    "sampling_rate": 16000,
+    "filter_length": 1280,
+    "hop_length": 320,
+    "win_length": 1280,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": null
+  },
+  "model": {
+    "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": [10,8,2,2],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [16,16,4,4],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256,
+    "ssl_dim": 1024,
+    "use_spk": true
+  }
+}