/content/project
TTSTrainer start 528.226516734
Initializing trainer with hparams:
{'attention_dim': 128,
 'attention_location_kernel_size': 31,
 'attention_location_n_filters': 32,
 'attention_rnn_dim': 1024,
 'batch_size': 10,
 'checkpoint_name': 'my-very-epic-model',
 'checkpoint_path': '/content/drive/MyDrive/tacotron',
 'coarse_n_frames_per_step': None,
 'config': 'tacotron2_config.json',
 'cudnn_enabled': True,
 'dataset_path': '.',
 'debug': False,
 'decay_rate': 8000,
 'decay_start': 15000,
 'decoder_rnn_dim': 1024,
 'distributed_run': False,
 'encoder_embedding_dim': 512,
 'encoder_kernel_size': 5,
 'encoder_n_convolutions': 3,
 'epochs': 69420,
 'epochs_per_checkpoint': 10,
 'filter_length': 1024,
 'fp16_run': False,
 'gate_threshold': 0.5,
 'grad_clip_thresh': 1.0,
 'gst_dim': 2304,
 'gst_type': 'torchmoji',
 'has_speaker_embedding': True,
 'hop_length': 256,
 'ignore_layers': ['speaker_embedding.weight',
                   'spkr_lin.weight',
                   'spkr_lin.bias'],
 'include_f0': False,
 'is_validate': True,
 'learning_rate': 0.001118033988749895,
 'log_dir': '/content/project/logs',
 'lrdecay_min': 0.00011180339887498949,
 'lrdecay_start': 150,
 'lrdecay_steps': 350,
 'mask_padding': True,
 'max_decoder_steps': 1000,
 'max_wav_value': 32768.0,
 'mel_fmax': 8000,
 'mel_fmin': 0,
 'n_frames_per_step_initial': 1,
 'n_mel_channels': 80,
 'n_speakers': 1,
 'num_heads': 8,
 'p_arpabet': 1.0,
 'p_attention_dropout': 0.1,
 'p_decoder_dropout': 0.1,
 'p_teacher_forcing': 1.0,
 'pos_weight': None,
 'postnet_embedding_dim': 512,
 'postnet_kernel_size': 5,
 'postnet_n_convolutions': 5,
 'prenet_dim': 256,
 'prenet_f0_dim': 1,
 'prenet_f0_kernel_size': 1,
 'prenet_f0_n_layers': 1,
 'prenet_fms_kernel_size': 1,
 'prenet_rms_dim': 0,
 'reduction_window_schedule': [{'batch_size': 16,
                                'n_frames_per_step': 1,
                                'until_step': 10000},
                               {'batch_size': 16,
                                'n_frames_per_step': 1,
                                'until_step': 50000},
                               {'batch_size': 16,
                                'n_frames_per_step': 1,
                                'until_step': 60000},
                               {'batch_size': 16,
                                'n_frames_per_step': 1,
                                'until_step': 70000},
                               {'batch_size': 16,
                                'n_frames_per_step': 1,
                                'until_step': None}],
 'ref_enc_filters': [32, 32, 64, 64, 128, 128],
 'ref_enc_gru_size': 128,
 'ref_enc_pad': [1, 1],
 'ref_enc_size': [3, 3],
 'ref_enc_strides': [2, 2],
 'sample_inference_speaker_ids': [0],
 'sample_inference_text': 'That quick beige fox jumped in the air loudly over '
                          'each thin dog.',
 'sampling_rate': 22050,
 'seed': 123,
 'speaker_embedding_dim': 128,
 'steps_per_sample': 15,
 'symbol_set': 'nvidia_taco2',
 'symbols_embedding_dim': 512,
 'text_cleaners': ['english_cleaners'],
 'torchmoji_model_file': 'pytorch_model.bin',
 'torchmoji_vocabulary_file': 'vocabulary.json',
 'training_audiopaths_and_text': 'transcription.txt',
 'val_audiopaths_and_text': 'transcription_val.txt',
 'warm_start_name': '/content/base_aitch.pt',
 'weight_decay': 1e-06,
 'win_length': 1024,
 'with_gst': True}
/usr/local/lib/python3.9/dist-packages/uberduck_ml_dev/models/torchmoji.py:1475: UserWarning: nn.init.uniform is now deprecated in favor of nn.init.uniform_.
  nn.init.uniform(self.embed.weight.data, a=-0.5, b=0.5)
/usr/local/lib/python3.9/dist-packages/uberduck_ml_dev/models/torchmoji.py:1477: UserWarning: nn.init.xavier_uniform is now deprecated in favor of nn.init.xavier_uniform_.
  nn.init.xavier_uniform(t)
/usr/local/lib/python3.9/dist-packages/uberduck_ml_dev/models/torchmoji.py:1479: UserWarning: nn.init.orthogonal is now deprecated in favor of nn.init.orthogonal_.
  nn.init.orthogonal(t)
/usr/local/lib/python3.9/dist-packages/uberduck_ml_dev/models/torchmoji.py:1481: UserWarning: nn.init.constant is now deprecated in favor of nn.init.constant_.
  nn.init.constant(t, 0)
/usr/local/lib/python3.9/dist-packages/uberduck_ml_dev/models/torchmoji.py:1483: UserWarning: nn.init.xavier_uniform is now deprecated in favor of nn.init.xavier_uniform_.
  nn.init.xavier_uniform(self.output_layer[0].weight.data)
start train 529.488128475
/usr/local/lib/python3.9/dist-packages/uberduck_ml_dev/models/common.py:230: FutureWarning: Pass size=1024 as keyword args. From version 0.10 passing these as positional arguments will result in an error
  fft_window = pad_center(fft_window, filter_length)
/usr/local/lib/python3.9/dist-packages/uberduck_ml_dev/models/common.py:357: FutureWarning: Pass sr=22050, n_fft=1024, n_mels=80, fmin=0, fmax=8000 as keyword args. From version 0.10 passing these as positional arguments will result in an error
  mel_basis = librosa_mel(
Initialized Torchmoji GST
Starting warm_start 533.831198587
WARNING! Attempting to load a model with out the speaker_embedding.weight layer. This could lead to unexpected results during evaluation.
Ending warm_start 533.91961055
Error while getting data: ['speakers/0000_WAV/WAV/8.wav', 'Easier said than done, I thought you were the one listening to my movie.', '0']
[Errno 2] No such file or directory: 'speakers/0000_WAV/WAV/8.wav'
Exception raised while training: [Errno 2] No such file or directory: 'speakers/0000_WAV/WAV/8.wav'
Traceback (most recent call last):
  File "/usr/lib/python3.9/runpy.py", line 197, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "/usr/lib/python3.9/runpy.py", line 87, in _run_code
    exec(code, run_globals)
  File "/usr/local/lib/python3.9/dist-packages/uberduck_ml_dev/exec/train_tacotron2.py", line 49, in <module>
    run(None, None, hparams)
  File "/usr/local/lib/python3.9/dist-packages/uberduck_ml_dev/exec/train_tacotron2.py", line 30, in run
    raise e
  File "/usr/local/lib/python3.9/dist-packages/uberduck_ml_dev/exec/train_tacotron2.py", line 26, in run
    trainer.train()
  File "/usr/local/lib/python3.9/dist-packages/uberduck_ml_dev/trainer/tacotron2.py", line 462, in train
    for batch_idx, batch in enumerate(train_loader):
  File "/usr/local/lib/python3.9/dist-packages/torch/utils/data/dataloader.py", line 628, in __next__
    data = self._next_data()
  File "/usr/local/lib/python3.9/dist-packages/torch/utils/data/dataloader.py", line 671, in _next_data
    data = self._dataset_fetcher.fetch(index)  # may raise StopIteration
  File "/usr/local/lib/python3.9/dist-packages/torch/utils/data/_utils/fetch.py", line 58, in fetch
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/usr/local/lib/python3.9/dist-packages/torch/utils/data/_utils/fetch.py", line 58, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/usr/local/lib/python3.9/dist-packages/uberduck_ml_dev/data_loader.py", line 232, in __getitem__
    data = self._get_data(self.audiopaths_and_text[idx])
  File "/usr/local/lib/python3.9/dist-packages/uberduck_ml_dev/data_loader.py", line 190, in _get_data
    sampling_rate, wav_data = read(path)
  File "/usr/local/lib/python3.9/dist-packages/scipy/io/wavfile.py", line 647, in read
    fid = open(filename, 'rb')
FileNotFoundError: [Errno 2] No such file or directory: 'speakers/0000_WAV/WAV/8.wav'