Error running whisperX about subsai HOT 3 OPEN

Turns out I was missing cuda, so managed to fix that,

Still working on the other issue.

from subsai.

Try smaller models and if they work then this is probably a WhsiperX issue, go to their repo and see if they support large-v3.

For Whisper-timestamped, you should see the cuda option if you have a cuda device.
If there is no cuda option despite having a cuda device then you should check if Pytorch GPU is installed correctly and can see your cuda device by running

import torch 

print(torch.cuda.is_available())

from subsai.

I'm getting this error with large-v2:

TypeError: TranscriptionOptions.__new__() missing 6 required positional arguments: 'repetition_penalty', 'no_repeat_ngram_size', 'prompt_reset_on_temperature', 'max_new_tokens', 'clip_timestamps', and 'hallucination_silence_threshold'

from subsai.