search

coqui-ai / TTS

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
http://coqui.ai
Mozilla Public License 2.0
35.48k stars 4.33k forks source link

[Bug] RuntimeError: Error opening '/content/TTS/filelists/wavs/"yoon-349.wav': System error. #999

Closed epona7471 closed 2 years ago

epona7471 commented 2 years ago

Welcome to the 🐸TTS project! We are excited to see your interest, and appreciate your support!

This repository is governed by the Contributor Covenant Code of Conduct. For more details, see the CODE_OF_CONDUCT.md file.

If you've found a bug, please provide the following information:

Describe the bug I am trying to use other dataset(Korean) and I don't know why this directory path includes "(quotation mark) in the middle with no reason during running. Check below error message and find the (") before yoon-349

RuntimeError: Error opening '/content/TTS/filelists/wavs/"yoon-349.wav': System error.

my metadata.csv does not include any quotation mark.

image

Do you have similar bugs reported?

To Reproduce Steps to reproduce the behavior:

My command is below

python TTS/bin/train_glow_tts.py \ --config_path "/content/drive/My Drive/Colab Notebooks/data/glowtts-v2/config.json" \ --coqpit.datasets.0.path "/content/TTS/filelists" \ --coqpit.audio.stats_path "/content/drive/My Drive/Colab Notebooks/data/glowtts-v2/scale_stats_new.npy" \ --coqpit.test_sentences_file "/content/TTS/test_sentences.txt" \ --coqpit.output_path "/content/drive/My Drive/Colab Notebooks/data/glowtts-v2/" \ --coqpit.num_loader_workers 2 \ --coqpit.num_val_loader_workers 2 \ --restore_path "/content/drive/My Drive/Colab Notebooks/data/glowtts-v2/model_file.pth.tar")

Expected behavior A clear and concise description of what you expected to happen.

Environment (please complete the following information):

Additional context

This is my full error script

/content/TTS

Using CUDA: True Number of GPUs: 1 Git Hash: 3aa165a Experiment folder: /content/drive/My Drive/Colab Notebooks/data/glowtts-v2/glowtts-v2-December-06-2021_07+16PM-3aa165a Setting up Audio Processor... | > sample_rate:22050 | > resample:False | > num_mels:80 | > min_level_db:-100 | > frame_shift_ms:None | > frame_length_ms:None | > ref_level_db:20 | > fft_size:1024 | > power:1.1 | > preemphasis:0.98 | > griffin_lim_iters:60 | > signal_norm:True | > symmetric_norm:True | > mel_fmin:0 | > mel_fmax:8000.0 | > spec_gain:20.0 | > stft_pad_mode:reflect | > max_norm:4.0 | > clip_norm:True | > do_trim_silence:False | > trim_db:60 | > do_sound_norm:False | > stats_path:/content/drive/My Drive/Colab Notebooks/data/glowtts-v2/scale_stats_new.npy | > base:10 | > hop_length:256 | > win_length:1024 | > Found 850 files in /content/TTS/filelists Using model: glow_tts /content/TTS/TTS/tts/layers/glow_tts/glow.py:84: UserWarning: torch.qr is deprecated in favor of torch.linalg.qr and will be removed in a future PyTorch release. The boolean parameter 'some' has been replaced with a string parameter 'mode'. Q, R = torch.qr(A, some) should be replaced with Q, R = torch.linalg.qr(A, 'reduced' if some else 'complete') (Triggered internally at ../aten/src/ATen/native/BatchLinearAlgebra.cpp:1937.) w_init = torch.qr(torch.FloatTensor(self.num_splits, self.numsplits).normal())[0] Restoring from model_file.pth.tar ... Model restored from step 26000

Model has 28612177 parameters Starting with inf best loss.

DataLoader initialization | > Use phonemes: False | > Number of instances : 842 | > Max length sequence: 46 | > Min length sequence: 6 | > Avg length sequence: 19.327790973871736 | > Num. instances discarded by max-min (max=500, min=3) seq limits: 0 | > Batch group size: 128.

DataLoader initialization | > Use phonemes: False | > Number of instances : 8 | > Max length sequence: 31 | > Min length sequence: 18 | > Avg length sequence: 22.125 | > Num. instances discarded by max-min (max=500, min=3) seq limits: 0 | > Batch group size: 0. Data depended initialization ... /content/TTS/TTS/tts/models/glow_tts.py:291: UserWarning: floordiv is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). y_lengths = (y_lengths // self.num_squeeze) * self.num_squeeze

EPOCH: 0/10000

TRAINING (2021-12-06 19:16:53) ! Run is removed from /content/drive/My Drive/Colab Notebooks/data/glowtts-v2/glowtts-v2-December-06-2021_07+16PM-3aa165a Traceback (most recent call last): File "TTS/bin/train_glow_tts.py", line 588, in main(args) File "TTS/bin/train_glow_tts.py", line 562, in main train_loader, model, criterion, optimizer, scheduler, ap, global_step, epoch File "TTS/bin/train_glow_tts.py", line 177, in train for num_iter, data in enumerate(data_loader): File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/dataloader.py", line 521, in next data = self._next_data() File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/dataloader.py", line 1203, in _next_data return self._process_data(data) File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/dataloader.py", line 1229, in _process_data data.reraise() File "/usr/local/lib/python3.7/dist-packages/torch/_utils.py", line 434, in reraise raise exception RuntimeError: Caught RuntimeError in DataLoader worker process 0. Original Traceback (most recent call last): File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/worker.py", line 287, in _worker_loop data = fetcher.fetch(index) File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/fetch.py", line 49, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/fetch.py", line 49, in data = [self.dataset[idx] for idx in possibly_batched_index] File "/content/TTS/TTS/tts/datasets/TTSDataset.py", line 273, in getitem return self.load_data(idx) File "/content/TTS/TTS/tts/datasets/TTSDataset.py", line 142, in load_data wav = np.asarray(self.load_wav(wav_file), dtype=np.float32) File "/content/TTS/TTS/tts/datasets/TTSDataset.py", line 87, in load_wav audio = self.ap.load_wav(filename) File "/content/TTS/TTS/utils/audio.py", line 386, in load_wav x, sr = sf.read(filename) File "/usr/local/lib/python3.7/dist-packages/soundfile.py", line 257, in read subtype, endian, format, closefd) as f: File "/usr/local/lib/python3.7/dist-packages/soundfile.py", line 629, in init self._file = self._open(file, mode_int, closefd) File "/usr/local/lib/python3.7/dist-packages/soundfile.py", line 1184, in _open "Error opening {0!r}: ".format(self.name)) File "/usr/local/lib/python3.7/dist-packages/soundfile.py", line 1357, in _error_check raise RuntimeError(prefix + _ffi.string(err_str).decode('utf-8', 'replace')) RuntimeError: Error opening '/content/TTS/filelists/wavs/"yoon-349.wav': System error.

stale[bot] commented 2 years ago

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions. You might also look our discussion channels.