reriiasu / speech-to-text

Real-time transcription using faster-whisper
MIT License
375 stars 56 forks source link

Acknowledgments #1

Open PINTO0309 opened 1 year ago

PINTO0309 commented 1 year ago

Your implementation is very nice! I thought I would post the issue as a thank you.

I found your implementation very helpful and would like to Dockerize it to help me implement it on my robot. Very cool how VAD and buffering works.

I immediately quoted a large part of your implementation and imported it into the Docker environment in my repository. https://github.com/PINTO0309/faster-whisper-env Operation is very good!

This issue is published only to express our gratitude and you are free to close it of your own free will. Again, thank you very much. :smile_cat:

Incidentally, at the risk of meddling, the current version of faster-whisper v0.6.0 works fine when weights are run over the network.