This seems to work for multi-speaker

2026-10-19 07:42:59 +00:00 · 2020-06-15 00:02:37 -04:00
parent 788eef5e1a
commit 6c72eda849
5 changed files with 178 additions and 0 deletions
@@ -0,0 +1,55 @@
+{
+  "train": {
+    "use_cuda": true,
+    "log_interval": 20,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 1e0,
+    "betas": [0.9, 0.98],
+    "eps": 1e-9,
+    "warmup_steps": 4000,
+    "scheduler": "noam",
+    "batch_size": 32,
+    "ddi": true,
+    "fp16_run": true
+  },
+  "data": {
+    "load_mel_from_disk": false,
+    "training_files":"/home/bt/datasets/voicecurator_training/training.csv",
+    "validation_files":"/home/bt/datasets/voicecurator_training/validation.csv",
+    "text_cleaners":["english_cleaners"],
+    "max_wav_value": 32768.0,
+    "sampling_rate": 22050,
+    "filter_length": 1024,
+    "hop_length": 256,
+    "win_length": 1024,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": 8000.0,
+    "add_noise": true,
+    "add_space": false,
+    "cmudict_path": "data/cmu_dictionary"
+  },
+  "model": {
+    "hidden_channels": 192,
+    "filter_channels": 768,
+    "filter_channels_dp": 256,
+    "kernel_size": 3,
+    "p_dropout": 0.1,
+    "n_blocks_dec": 12,
+    "n_layers_enc": 6,
+    "n_heads": 2,
+    "p_dropout_dec": 0.05,
+    "dilation_rate": 1,
+    "kernel_size_dec": 5,
+    "n_block_layers": 4,
+    "n_sqz": 2,
+    "prenet": true,
+    "mean_only": true,
+    "hidden_channels_enc": 192,
+    "hidden_channels_dec": 192,
+    "window_size": 4,
+    "n_speakers": 64,
+    "gin_channels": 256
+  }
+}