FileNotFoundError: [Errno 2] No such file or directory: 'DUMMY/LJ009-0042.wav'

[Aliraheem]

Hello everyone, I am trying to run Tacotron2. I am having this error below: Any suggestion, please?

WARNING:tensorflow: The TensorFlow contrib module will not be included in TensorFlow 2.0. For more information, please see:

• https://github.com/tensorflow/community/blob/master/rfcs/20180907-contrib-sunset.md
• https://github.com/tensorflow/addons
• https://github.com/tensorflow/io (for I/O related ops) If you depend on functionality not listed there, please file an issue.

FP16 Run: False Dynamic Loss Scaling: True Distributed Run: False cuDNN Enabled: True cuDNN Benchmark: False Epoch: 0 Traceback (most recent call last): File "train.py", line 290, in args.warm_start, args.n_gpus, args.rank, args.group_name, hparams) File "train.py", line 208, in train for i, batch in enumerate(train_loader): File "/home/ali/.local/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 521, in next data = self._next_data() File "/home/ali/.local/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 1203, in _next_data return self._process_data(data) File "/home/ali/.local/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 1229, in _process_data data.reraise() File "/home/ali/.local/lib/python3.6/site-packages/torch/_utils.py", line 425, in reraise raise self.exc_type(msg) FileNotFoundError: Caught FileNotFoundError in DataLoader worker process 0. Original Traceback (most recent call last): File "/home/ali/.local/lib/python3.6/site-packages/torch/utils/data/_utils/worker.py", line 287, in _worker_loop data = fetcher.fetch(index) File "/home/ali/.local/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/home/ali/.local/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 44, in data = [self.dataset[idx] for idx in possibly_batched_index] File "/home/ali/tacotron2/data_utils.py", line 61, in getitem return self.get_mel_text_pair(self.audiopaths_and_text[index]) File "/home/ali/tacotron2/data_utils.py", line 34, in get_mel_text_pair mel = self.get_mel(audiopath) File "/home/ali/tacotron2/data_utils.py", line 39, in get_mel audio, sampling_rate = load_wav_to_torch(filename) File "/home/ali/tacotron2/utils.py", line 14, in load_wav_to_torch sampling_rate, data = read(full_path) File "/home/ali/.local/lib/python3.6/site-packages/scipy/io/wavfile.py", line 233, in read fid = open(filename, 'rb') FileNotFoundError: [Errno 2] No such file or directory: 'DUMMY/LJ009-0042.wav'

[CookiePPP]

https://github.com/NVIDIA/tacotron2#setup

step 5 of setup. Replace DUMMY with the path to your LJSpeech dataset audio folder.

[DivyanshRathi]

I am facing the same problem, and I have implemented step 5 of setup, instead of "DUMMY" in the last line, it says the following. No such file or directory: 'ljs_dataset_folder/wavs/LJ009-0042.wav'

I checked all the files and didn't find this file either.

[urmikakasi]

Did you find a solution to this? I'm having the same issue too.

[Aliraheem]

The directories of waves in train and validation files (tacotron2/filelists/) should be the same as your dataset path. Use this command to update them: Update .wav paths: sed -i -- 's,DUMMY,ljs_dataset_folder/wavs,g' filelists/*.txt

[postovalov]

For example, for colab users, if you are loading the LJSpeech dataset into "content" folder and unzipped it in the same location, use this command with absolute path:

sed -i -- 's,/content/LJSpeech-1.1./wavs,ljs_dataset_folder/wavs,g' filelists/*.txt

[a897456]

I copy the files from LJSpeech-1.1 into the DUMMY folder