LTX2.3 data process when input_audio process error

[starcloud530]

Traceback (most recent call last):
File "/root/autodl-tmp/DiffSynth-Studio/examples/ltx2/model_training/train.py", line 179, in
launcher_map[args.task](accelerator, dataset, model, model_logger, args=args)
File "/root/autodl-tmp/DiffSynth-Studio/diffsynth/diffusion/runner.py", line 65, in launch_data_process_task
for data_id, data in enumerate(tqdm(dataloader)):
File "/root/miniconda3/lib/python3.12/site-packages/tqdm/std.py", line 1181, in iter
for obj in iterable:
File "/root/miniconda3/lib/python3.12/site-packages/accelerate/data_loader.py", line 567, in iter
current_batch = next(dataloader_iter)
^^^^^^^^^^^^^^^^^^^^^
File "/root/miniconda3/lib/python3.12/site-packages/torch/utils/data/dataloader.py", line 734, in next
data = self._next_data()
^^^^^^^^^^^^^^^^^
File "/root/miniconda3/lib/python3.12/site-packages/torch/utils/data/dataloader.py", line 790, in _next_data
data = self._dataset_fetcher.fetch(index) # may raise StopIteration
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/miniconda3/lib/python3.12/site-packages/torch/utils/data/_utils/fetch.py", line 52, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
~~~~~~~~~~~~^^^^^
File "/root/autodl-tmp/DiffSynth-Studio/diffsynth/core/data/unified_dataset.py", line 98, in getitem
data[key] = self.special_operator_mapkey
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/autodl-tmp/DiffSynth-Studio/diffsynth/core/data/operators.py", line 14, in call
data = operator(data)
^^^^^^^^^^^^^^
File "/root/autodl-tmp/DiffSynth-Studio/diffsynth/core/data/operators.py", line 266, in call
waveform, sample_rate = torchaudio.load(data)
^^^^^^^^^^^^^^^^^^^^^
File "/root/miniconda3/lib/python3.12/site-packages/torchaudio/_backend/utils.py", line 222, in load
return backend.load(uri, frame_offset, num_frames, normalize, channels_first, format, buffer_size)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/miniconda3/lib/python3.12/site-packages/torchaudio/_backend/soundfile.py", line 27, in load
return soundfile_backend.load(uri, frame_offset, num_frames, normalize, channels_first, format)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/miniconda3/lib/python3.12/site-packages/torchaudio/backend/soundfile_backend.py", line 221, in load
with soundfile.SoundFile(filepath, "r") as file:
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/miniconda3/lib/python3.12/site-packages/soundfile.py", line 690, in init
self._file = self._open(file, mode_int, closefd)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/miniconda3/lib/python3.12/site-packages/soundfile.py", line 1265, in _open
raise LibsndfileError(err, prefix="Error opening {0!r}: ".format(self.name))
soundfile.LibsndfileError: Error opening 'data/ltx2.3/LTX-doggy-style/0001.mp4': Format not recognised.
Traceback (most recent call last):
File "/root/miniconda3/bin/accelerate", line 8, in

[mi804]

This issue arises because the older version of torchaudio relied on an external backend, whereas the latest version of torchaudio that we use employs the TorchCodec backend. We recommend upgrading both torch and torchaudio to their latest versions, and installing TorchCodec via pip install torchcodec.