search

alesaccoia / VoiceStreamAI

Near-Realtime audio transcription using self-hosted Whisper and WebSocket in Python/JS
MIT License
736 stars 106 forks source link

how can I deploy with my local model (e.g. faster_whisper_large_v3)? #19

Open ruifengma opened 6 months ago

ruifengma commented 6 months ago

as title

alesaccoia commented 6 months ago

That's the goal of the project and it works out of the box. What's the issue you're experiencing?

ruifengma commented 6 months ago

That's the goal of the project and it works out of the box. What's the issue you're experiencing?

Thanks for you reply, I actually wish to pre-download the model weights (faster_whisper and segmentation) to deploy the service due to some special network issue.

kenho211 commented 4 months ago

from_pretrained allow huggingface model name OR model file path.