-
Notifications
You must be signed in to change notification settings - Fork 1k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Hotwords not respected after PR #856 #1076
Comments
@MahmoudAshraf97 will you find time to take a look? Thx. |
I will, can you share the output before # 856? |
segments, info = model.transcribe(input_file, hotwords="the video is about comfyUI", beam_size=5, language="en", vad_filter=False, vad_parameters = dict(min_silence_duration_ms=1000))
I tested on different materials. It seems like the hotwords option is not respected. |
@MahmoudAshraf97 I forgot to add - the hotwords option is not respected in standard and batching interference. |
I just tested the video you shared and hotwords worked as expected on several models, although smaller models were less affected, but still affected nonetheless. As for batched transcription, I'm working on adding hotwords support. |
the test video is https://www.youtube.com/watch?v=Ybu6qTbEsew
if no hotwords
the result is:
if add hotwords
the result is same:
The text was updated successfully, but these errors were encountered: