saharmor/whisper-playground
Build real time speech2text web apps using OpenAI's Whisper https://openai.com/blog/whisper/
PythonMIT
Issues
- 1
Online demo is down
#48 opened by samueldashadrach - 0
- 14
USING THIS SETUP ON CPU
#42 opened by shanky100 - 0
Implement parameter validation in the client
#46 opened by ethanzrd - 0
Moving the backend's IP into config.js
#43 opened by saharmor - 0
Implement status bar
#44 opened by ethanzrd - 0
Add auto-scroll for transcribed data in client
#33 opened by ethanzrd - 1
Code switching inputs
#19 opened by jayakrishnanmm - 7
Purple dots keep going & no transcription.
#6 opened by BrianFenn - 0
- 0
Implement multi-client support
#41 opened by ethanzrd - 0
Prevent errors with speechless batches
#36 opened by ethanzrd - 5
Error occurred during backend connection.
#34 opened by Epresin - 2
The backend is not available on Windows.
#30 opened by Epresin - 0
- 0
- 0
Dockerized the fullstack app
#24 opened by saharmor - 0
.... this is for future issues
#20 opened by mjund - 4
Possible to package this in a dockerfile?
#17 opened by benwhalley - 6
`yarn start` error
#14 opened by yubrshen - 2
sh: 1: react-scripts: not found
#15 opened by developertrinidad08 - 1
Stucking on three purple dots
#4 opened by tamto6666 - 2
Use pyannote-audio for speaker diarization
#10 opened by saharmor - 2
Backend error : AttributeError: module 'whisper' has no attribute 'load_model'
#11 opened by OK-Cactus - 1
- 0
Use whisper.cpp for faster CPU inference
#9 opened by saharmor - 6
Pyaudio
#2 opened by Alastair1234 - 7
- 1