search

SevaSk / ecoute

Ecoute is a live transcription tool that provides real-time transcripts for both the user's microphone input (You) and the user's speakers output (Speaker) in a textbox. It also generates a suggested response using OpenAI's GPT-3.5 for the user to say based on the live transcription of the conversation.
https://github.com/SevaSk/ecoute
MIT License
5.85k stars 817 forks source link

how configure to listen in Russian language? #9

Closed cool102 closed 1 year ago

cool102 commented 1 year ago

Hi, very cool! Its working! So cool! How configure to listen in Russian language?

SevaSk commented 1 year ago

Thanks! Out of the box, one of the limitations is that it's only designed for English. To modify the code so it works with Russian, you would have to update the AudioTranscriber class with the appropriate non-English Whisper model. Here is the Whisper documentation for you to follow: https://github.com/openai/whisper/blob/main/README.md.

SevaSk commented 1 year ago

I created an issue https://github.com/SevaSk/ecoute/issues/11 for added multi language support.

cool102 commented 1 year ago

When are you planning to finalize the multilingual feature?