chengsokdara/use-whisper
React hook for OpenAI Whisper with speech recorder, real-time transcription, and silence removal built-in
TypeScriptMIT
Issues
- 6
Module not found: Can't resolve '/node_modules/@ffmpeg/core/dist/ffmpeg-core.js'
#40 opened by AlanHazel - 1
It does not seem to work for any reason
#26 opened by debugger-anubhav - 5
- 1
difference in the pitch and speed
#53 opened by shawnchiao - 0
- 6
- 3
Is the repo actively maintained
#54 opened by d-ivashchuk - 0
- 0
Getting undefined in output for transcript
#56 opened by ashwin-maurya - 6
Transcript object always undefined
#7 opened by ajesuscode - 3
- 5
- 4
- 0
Feature Request: Retry transcription using previous recording on internet connectivity error
#52 opened by zackseyun - 0
Error on deploying
#39 opened by anuragsingh922 - 0
Add error handling
#51 opened by chrysb - 0
Module parse failed: Unexpected token
#50 opened by XyzAQWERTY - 0
error while streaming or after stop recording POST https://api.openai.com/v1/audio/transcriptions 401
#48 opened by alihinnawe - 1
- 0
Integrate Monsterapi Whisper ASR
#47 opened by gvijqb - 1
Exposing api key
#43 opened by LeonardoTrapani - 0
- 7
Issues with vite dev server
#23 opened by kvndrsslr - 0
- 0
Any way to disable all these console.logs?
#37 opened by oalexdoda - 0
uncaught TypeError: Cannot read properties of null (reading 'useRef') at useRef
#36 opened by moorthi07 - 0
Input a rtmp stream
#35 opened by aledezma9 - 0
Issues using it on replit
#24 opened by Borahm - 0
Microphone Selection
#31 opened by n1developer-ubt - 5
It just doesn't work for me for a reason
#18 opened by y-71 - 0
Reset to the default value transcript object
#30 opened by Olha-Diachek - 1
Issue chaining actions
#27 opened by athrael-soju - 0
Suggested mode
#25 opened by TomYeoman - 0
please add more examples
#22 opened by street-grease-coder - 1
Module not found @ffmpeg/core
#19 opened by xkrsz - 4
Invalid file format
#10 opened by leopoldpoldus - 1
- 2
Safari support?
#13 opened by sgrove - 0
- 1
- 0
- 9
Is it possible to capture the state if the user is currently speaking or not in the object that is returned by the hook?
#5 opened by sanesanyo - 2
Apologies for the confusion. But I wanted to have automatic translation to English of the transcribed text set to False.
#4 opened by sanesanyo