upload files

finetune_speaker.py

@@ -78,7 +78,7 @@ def run(rank, n_gpus, hps):
       rank=rank,
       shuffle=True)
   collate_fn = TextAudioSpeakerCollate()
-  train_loader = DataLoader(train_dataset, num_workers=0, shuffle=False, pin_memory=True,
+  train_loader = DataLoader(train_dataset, num_workers=8, shuffle=False, pin_memory=True,
       collate_fn=collate_fn, batch_sampler=train_sampler)
   # train_loader = DataLoader(train_dataset, batch_size=hps.train.batch_size, num_workers=0, shuffle=False, pin_memory=True,
   #                           collate_fn=collate_fn)

requirements.txt

@@ -3,6 +3,9 @@ librosa
 numpy
 scipy
 tensorboard
+torch --extra-index-url https://download.pytorch.org/whl/cu116
+torchvision --extra-index-url https://download.pytorch.org/whl/cu116
+torchaudio --extra-index-url https://download.pytorch.org/whl/cu116
 unidecode
 pyopenjtalk
 jamo
@@ -17,4 +20,5 @@ indic_transliteration==2.3.37
 num_thai==0.0.5
 opencc==1.1.1
 demucs
+openai-whisper
 gradio