Loading README.md +4 −4 Original line number Diff line number Diff line Loading @@ -30,7 +30,7 @@ soundstream = SoundStream( trainer = SoundStreamTrainer( soundstream, folder = '/path/to/librispeech', folder = '/path/to/audio/files', batch_size = 4, grad_accum_every = 8, # effective batch size of 32 data_max_length = 320 * 32, Loading Loading @@ -67,7 +67,7 @@ semantic_transformer = SemanticTransformer( trainer = SemanticTransformerTrainer( transformer = semantic_transformer, wav2vec = wav2vec, folder = '/home/phil/dl/data/LibriSpeech', folder ='/path/to/audio/files', batch_size = 1, data_max_length = 320 * 32, num_train_steps = 1 Loading Loading @@ -106,7 +106,7 @@ trainer = CoarseTransformerTrainer( transformer = coarse_transformer, soundstream = soundstream, wav2vec = wav2vec, folder = '/home/phil/dl/data/LibriSpeech', folder = '/path/to/audio/files', batch_size = 1, data_max_length = 320 * 32, num_train_steps = 10000 Loading Loading @@ -139,7 +139,7 @@ fine_transformer = FineTransformer( trainer = FineTransformerTrainer( transformer = fine_transformer, soundstream = soundstream, folder = '/home/phil/dl/data/LibriSpeech', folder = '/path/to/audio/files', batch_size = 1, data_max_length = 320 * 32, num_train_steps = 10000 Loading Loading
README.md +4 −4 Original line number Diff line number Diff line Loading @@ -30,7 +30,7 @@ soundstream = SoundStream( trainer = SoundStreamTrainer( soundstream, folder = '/path/to/librispeech', folder = '/path/to/audio/files', batch_size = 4, grad_accum_every = 8, # effective batch size of 32 data_max_length = 320 * 32, Loading Loading @@ -67,7 +67,7 @@ semantic_transformer = SemanticTransformer( trainer = SemanticTransformerTrainer( transformer = semantic_transformer, wav2vec = wav2vec, folder = '/home/phil/dl/data/LibriSpeech', folder ='/path/to/audio/files', batch_size = 1, data_max_length = 320 * 32, num_train_steps = 1 Loading Loading @@ -106,7 +106,7 @@ trainer = CoarseTransformerTrainer( transformer = coarse_transformer, soundstream = soundstream, wav2vec = wav2vec, folder = '/home/phil/dl/data/LibriSpeech', folder = '/path/to/audio/files', batch_size = 1, data_max_length = 320 * 32, num_train_steps = 10000 Loading Loading @@ -139,7 +139,7 @@ fine_transformer = FineTransformer( trainer = FineTransformerTrainer( transformer = fine_transformer, soundstream = soundstream, folder = '/home/phil/dl/data/LibriSpeech', folder = '/path/to/audio/files', batch_size = 1, data_max_length = 320 * 32, num_train_steps = 10000 Loading