upload files

finetune_speaker.py

@@ -150,7 +150,7 @@ def train_and_evaluate(rank, epoch, hps, nets, optims, schedulers, scaler, loade
 
   net_g.train()
   net_d.train()
-  for batch_idx, (x, x_lengths, spec, spec_lengths, y, y_lengths, speakers) in enumerate(train_loader):
+  for batch_idx, (x, x_lengths, spec, spec_lengths, y, y_lengths, speakers) in enumerate(tqdm(train_loader)):
     x, x_lengths = x.cuda(rank, non_blocking=True), x_lengths.cuda(rank, non_blocking=True)
     spec, spec_lengths = spec.cuda(rank, non_blocking=True), spec_lengths.cuda(rank, non_blocking=True)
     y, y_lengths = y.cuda(rank, non_blocking=True), y_lengths.cuda(rank, non_blocking=True)

utils.py

@@ -152,7 +152,7 @@ def get_hparams(init=True):
                         help='JSON file for configuration')
     parser.add_argument('-m', '--model', type=str, default="pretrained_models",
                         help='Model name')
-    parser.add_argument('-n', '--max_epochs', type=int, default="50",
+    parser.add_argument('-n', '--max_epochs', type=int, default=50,
                         help='finetune epochs')
 
     args = parser.parse_args()

whisper_transcribe.py

@@ -81,7 +81,7 @@ if __name__ == "__main__":
     with open("./configs/finetune_speaker.json", 'r', encoding='utf-8') as f:
         hps = json.load(f)
     # modify n_speakers
-    hps['data']["n_speakers"] = 999 + len(speaker2id)
+    hps['data']["n_speakers"] = 1000 + len(speaker2id)
     # add speaker names
     for speaker in speaker_names:
         hps['speakers'][speaker] = speaker2id[speaker]