Ive tried everything RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory

[Lucyan11]

It was working great, then my power went out during a sess and poof, this error. Ive tried EVERYTHING except he right thing, please help

windows 10, followed instructions, was working now its not

(voice) D:\VoiceSynth\tortoise-tts>python tortoise/do_tts.py --text "I'm going to speak this" --voice random --preset fast
Traceback (most recent call last):
File "tortoise/do_tts.py", line 27, in
tts = TextToSpeech(models_dir=args.model_dir)
File "D:\VoiceSynth\tortoise-tts\tortoise\api.py", line 236, in init
self.diffusion.load_state_dict(torch.load(get_model_path('diffusion_decoder.pth', models_dir)))
File "C:\Users\c_law\Anaconda3\envs\voice\lib\site-packages\torch\serialization.py", line 777, in load
with _open_zipfile_reader(opened_file) as opened_zipfile:
File "C:\Users\c_law\Anaconda3\envs\voice\lib\site-packages\torch\serialization.py", line 282, in init
super(_open_zipfile_reader, self).init(torch._C.PyTorchFileReader(name_or_buffer))
RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory

[neonbjb]

Your diffusion_decoder.pth file is corrupt. Clear out ~/.cache/tortoise.

[Lohnii]

This was happening to me as well and I got rid of it by downloading the models manually (you can find the urls in api.py) and moving them to C:\Users{YOUR USER}.cache\tortoise\models

[manmay-nakhashi]

@Lohnii error might be coming in wav2vec model can you check ? , you might delete it and download that again.

[Lohnii]

I don't know which model it came from but I have a problem with huggingface where I get an error when i try to download large models from the command line, so i downloaded them manually and that fixed it, thanks!