search

HenestrosaDev / audiotext

A desktop application that transcribes audio from files, microphone input or YouTube videos with the option to translate the content and create subtitles.
Other
103 stars 10 forks source link

I am encountering an error while using the software.[Bug] #38

Open chichi1314520 opened 3 days ago

chichi1314520 commented 3 days ago

Traceback (most recent call last): File "handlers\whisperx_handler.py", line 53, in transcribe_file File "whisperx\alignment.py", line 73, in load_align_model align_model = bundle.get_model(dl_kwargs={"model_dir": model_dir}).to(device) File "torchaudio\pipelines_wav2vec2\impl.py", line 126, in get_model File "torchaudio\pipelines_wav2vec2\impl.py", line 202, in _get_state_dict File "torchaudio\pipelines_wav2vec2\impl.py", line 89, in _get_state_dict File "torch\hub.py", line 750, in load_state_dict_from_url return torch.load(cached_file, map_location=map_location) File "torch\serialization.py", line 797, in load with _open_zipfile_reader(opened_file) as opened_zipfile: File "torch\serialization.py", line 283, in init super().init(torch._C.PyTorchFileReader(name_or_buffer)) RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory 图片

HenestrosaDev commented 3 days ago

According to this StackOverflow post, it appears that the model file is corrupted due to an incomplete download or an interruption in the process. Have you tried deleting the Audiotext folder and unzipping the audiotext-v2.2.3.zip file again? If you have done so and still get the same error, can you try running Audiotext on a different computer? I've also read in this GitHub issue that it might be due to disk space issues that happen when saving model checkpoints.