Whisper Realtime endpoint
Closed this issue · 2 comments
AbhijithMallya commented
I have self hosted whisper using speaches. The /v1/audio/transcriptions is working fine. It supports streaming output for complete audio .
However , I came across Realtime API Endpoint which mentions this can be used for transcription-only use cases(stream in and out). I believe whisper is enough for transcription only use-case.
In the documentation I didnt find a sample python implementation of the realtime endpoint. I would be grateful if anyone could help me with a simple python client for using wss://<host>:<port>/v1/realtime?intent=transcription.
github-actions commented
This issue is stale because it has been open for 7 days with no activity.
github-actions commented
This issue was closed because it has been inactive for 3 days since being marked as stale.