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
5.72k stars 794 forks source link

Add Multilanguage Support #11

Open SevaSk opened 1 year ago

SevaSk commented 1 year ago

Currently, we are using the English Whisper model for transcribing and we are responding in English as well. One possible improvement would be to add a dropdown menu for selecting the desired language for transcription and response generation which sets the appropriate models can be used in the code.

Adarsha-gg commented 1 year ago

Hey, can I get this assigned to me? I've made some decent progress.

lengkq commented 1 year ago

how to use in Chinese language?

Adarsha-gg commented 1 year ago

Hey @lengkq I'm sorry that it is taking long but once the pull request gets merged you will have a option to choose any language that you'd like to use. The feature isn't available "yet".

SevaSk commented 1 year ago

Hey just pushed a change where 

python main.py --api

Works in most languages!

suansuanchen commented 1 year ago

有日语吗？

NEUCFgod commented 1 year ago

Hello， is this demo favor of Chinese now？

ncesar commented 1 year ago

hey, what if I want to hardcode the language to english but still use the --api?

foryourever commented 4 months ago

Hey just pushed a change where

python main.py --api

Works in most languages!

but it doesn‘t works, I use '--api' and ecoute also recognized the Chinese to English

mang0sw33t commented 4 months ago

Try https://github.com/vivekuppal/transcribe/ It supports transcription in chinese and all the languages supported by openAI

Chinese
foryourever commented 4 months ago

收到

mang0sw33t commented 4 months ago

期待它