Skip to content
Discussion options

You must be logged in to vote

Hi! The first warning may happen if the model download was aborted during the previous try, and the second warning just means the calculation will happen in a slower but higher-precision format. They are both safe to ignore.

My guess is that because you're not using a GPU, it's just taking too long to transcribe the audio, especially when there are lots of words spoken in the audio. If you specify --model tiny.en, it will run faster than the default small model that you're using.

If you don't currently have a GPU, you can try the example notebooks like this one on Google Colab which provides a GPU runtime.

Replies: 2 comments 3 replies

Comment options

You must be logged in to vote
1 reply
@orangeduu
Comment options

Answer selected by jongwook
Comment options

You must be logged in to vote
2 replies
@SAR-hub
Comment options

@xiaofanloveme
Comment options

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet
4 participants