Training error: RuntimeError: Could not infer dtype of NoneType
#6
Open
opened 
Loading…
Reference in New Issue
There is no content yet.
Delete Branch "%!s(<nil>)"
Deleting a branch is permanent. It CANNOT be undone. Continue?
I get this error message when I try training a model. Here is the zip file containing the files causing the errors
https://files.catbox.moe/q9shx6.zip
Traceback (most recent call last):
File "/usr/lib/python3.10/runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/usr/lib/python3.10/runpy.py", line 86, in _run_code
exec(code, run_globals)
File "/home/user/ai-voice-cloning/modules/vall-e/vall_e/train.py", line 170, in
main()
File "/home/user/ai-voice-cloning/modules/vall-e/vall_e/train.py", line 163, in main
trainer.train(
File "/home/user/ai-voice-cloning/modules/vall-e/vall_e/utils/trainer.py", line 249, in train
for batch in _make_infinite_epochs(train_dl):
File "/home/user/ai-voice-cloning/modules/vall-e/vall_e/utils/trainer.py", line 199, in _make_infinite_epochs
yield from tqdm(dl, "Epoch progress", dynamic_ncols=True)
File "/home/user/ai-voice-cloning/venv/lib/python3.10/site-packages/tqdm/std.py", line 1182, in iter
for obj in iterable:
File "/home/user/ai-voice-cloning/venv/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 633, in next
data = self._next_data()
File "/home/user/ai-voice-cloning/venv/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 1325, in _next_data
return self._process_data(data)
File "/home/user/ai-voice-cloning/venv/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 1371, in _process_data
data.reraise()
File "/home/user/ai-voice-cloning/venv/lib/python3.10/site-packages/torch/_utils.py", line 644, in reraise
raise exception
RuntimeError: Caught RuntimeError in DataLoader worker process 3.
Original Traceback (most recent call last):
File "/home/user/ai-voice-cloning/venv/lib/python3.10/site-packages/torch/utils/data/_utils/worker.py", line 308, in _worker_loop
data = fetcher.fetch(index)
File "/home/user/ai-voice-cloning/venv/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/user/ai-voice-cloning/venv/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/user/ai-voice-cloning/modules/vall-e/vall_e/data.py", line 286, in getitem
text = torch.tensor([*map(self.phone_symmap.get, _get_phones(path))]).to(self.text_dtype)
RuntimeError: Could not infer dtype of NoneType
[2023-08-26 17:39:28,803] [INFO] [launch.py:315:sigkill_handler] Killing subprocess 32045
[2023-08-26 17:39:28,803] [ERROR] [launch.py:321:sigkill_handler] ['/home/user/ai-voice-cloning/venv/bin/python3.10', '-u', '-m', 'vall_e.train', '--local_rank=0', 'yaml=/home/user/ai-voice-cloning/training/Merida/config.yaml'] exits with return code = 1
You'll either need to:
./vall_e/data.py:35with the first line printed out when the dataset loads (it'll look like the existing symmap, but with more entries).It used to automatically update the symmap just-in-time rather than ahead-of-time, but doing so incurred a penalty when using an extremely large dataset.
I created the HDF5 dataset. I still got the "RuntimeError: Could not infer dtype of NoneType" error message. I tried setting to "True" under use_hdf5: in config.yaml and I got this error message
raise ValueError("No valid path is found for training.") ValueError: No valid path is found for training.