reriiasu/speech-to-text

About runtime errors

tsushimahiroaki opened this issue · 3 comments

tsushimahiroaki commented

nice to meet you. When I tried using the tool, the following error appeared on the UI. What should I do? Thank you.

[Error number 2] No such file or directory: 'C:\Users\username\.cache\huggingface\hub\models--guillaumekln--faster-whisper-medium\refs\ \main'

reriiasu commented

@tsushimahiroaki
hello tsushimahiroaki

The medium model may not have been downloaded.
Please check if the folder with the error exists.
If it exists, try deleting it.

tsushimahiroaki commented

thanks.

An error occured while synchronizing the model guillaumekln/faster-whisper-medium from the Hugging Face Hub:
HTTPSConnectionPool(host='huggingface.co', port=443): Max retries exceeded with url: /api/models/guillaumekln/faster-whisper-medium/revision/main (Caused by SSLError(SSLCertVerificationError(1, '[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1007)')))
Trying to load the model directly from the local cache, if it exists.
index.html was closed

I am getting the above error.
What should I do now.

reriiasu commented

You can manually deploy the model instead of using automatic model download.
Please refer to the next step.

  1. Manually download the following file from https://huggingface.co/guillaumekln/faster-whisper-medium.
    .gitattributes
    README.md
    config.json
    model.bin
    tokenizer.json
    vocabulary.txt

  2. Move the downloaded files to the speech-to-text\local_model directory.

  3. Change parameters from the UI.
    Set Model Settings > Model Size or Path to local_model.