RuntimeError: Couldn't find appropriate backend to handle uri ......./LJ001-0032.wav and format None.

[bowiesimon9]

log.txt
env.log
from https://github.com/speechbrain/speechbrain/tree/develop/recipes/LJSpeech/TTS
I do it , and get this:

python3 train.py --device=cuda:0 --max_grad_norm=1.0 --data_folder=/home/bowie/myTTS/data/LJSpeech-1.1 hparams/train.yaml
speechbrain.core - Beginning experiment!
speechbrain.core - Experiment folder: ./results/tacotron2/1234
ljspeech_prepare - Skipping preparation, completed in previous run.
speechbrain.core - 28.2M trainable parameters in Tacotron2Brain
speechbrain.utils.checkpoints - Would load a checkpoint here, but none found yet.
speechbrain.utils.epoch_loop - Going into epoch 1
0%| | 0/5887 [00:00<?, ?it/s]
speechbrain.core - Exception:
Traceback (most recent call last):
File "/home/bowie/myTTS/speechbrain/recipes/LJSpeech/TTS/tacotron2/train.py", line 387, in
tacotron2_brain.fit(
File "/home/bowie/.local/lib/python3.10/site-packages/speechbrain/core.py", line 1264, in fit
self._fit_train(train_set=train_set, epoch=epoch, enable=enable)
File "/home/bowie/.local/lib/python3.10/site-packages/speechbrain/core.py", line 1111, in _fit_train
for batch in t:
File "/home/bowie/.local/lib/python3.10/site-packages/tqdm/std.py", line 1182, in iter
for obj in iterable:
File "/home/bowie/.local/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 630, in next
data = self._next_data()
File "/home/bowie/.local/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 1345, in _next_data
return self._process_data(data)
File "/home/bowie/.local/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 1371, in _process_data
data.reraise()
File "/home/bowie/.local/lib/python3.10/site-packages/torch/_utils.py", line 694, in reraise
raise exception
RuntimeError: Caught RuntimeError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/home/bowie/.local/lib/python3.10/site-packages/torch/utils/data/_utils/worker.py", line 308, in _worker_loop
data = fetcher.fetch(index)
File "/home/bowie/.local/lib/python3.10/site-packages/torch/utils/data/_utils/fetch.py", line 51, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/bowie/.local/lib/python3.10/site-packages/torch/utils/data/_utils/fetch.py", line 51, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/bowie/.local/lib/python3.10/site-packages/speechbrain/dataio/dataset.py", line 165, in getitem
return self.pipeline.compute_outputs({"id": data_id, **data_point})
File "/home/bowie/.local/lib/python3.10/site-packages/speechbrain/utils/data_pipeline.py", line 464, in compute_outputs
return self._compute(data, self._exec_order, self.output_mapping)
File "/home/bowie/.local/lib/python3.10/site-packages/speechbrain/utils/data_pipeline.py", line 496, in _compute
values = item(*args) # Call the DynamicItem to produce output
File "/home/bowie/.local/lib/python3.10/site-packages/speechbrain/utils/data_pipeline.py", line 72, in call
return self.func(*args)
File "/home/bowie/myTTS/speechbrain/recipes/LJSpeech/TTS/tacotron2/train.py", line 317, in audio_pipeline
audio = sb.dataio.dataio.read_audio(wav)
File "/home/bowie/.local/lib/python3.10/site-packages/speechbrain/dataio/dataio.py", line 275, in read_audio
audio, _ = torchaudio.load(waveforms_obj)
File "/home/bowie/.local/lib/python3.10/site-packages/torchaudio/_backend/utils.py", line 202, in load
backend = dispatcher(uri, format, backend)
File "/home/bowie/.local/lib/python3.10/site-packages/torchaudio/_backend/utils.py", line 114, in dispatcher
raise RuntimeError(f"Couldn't find appropriate backend to handle uri {uri} and format {format}.")
RuntimeError: Couldn't find appropriate backend to handle uri /home/bowie/myTTS/data/LJSpeech-1.1/wavs/LJ001-0032.wav and format None.

the strange thing is: I have deleted file LJ001-0032.wav.
after this error happened many times, so I deleted the LJ001-0032.wav and deleted the LJ001-0032 item from metadata.csv, but the error still happened.

[bowiesimon9]

and I have successfully run this example on win10 wsl2. but when I change to Ubuntu22.04, the above error happened.
I deleted the results and run again , this time the error occurs at LJ001-0033.wav. so why is it just the 32th item?

btw, I used the main branch, the develop branch's code has error.

[bowiesimon9]

after I install soundfile. It worked.
so the question is: soundfile is for windows, why ubuntu need soundfile.