Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / saharmor/whisper-playground issues and pull requests
#49 - Integrate MonsterAPI for Advanced Audio Transcription in Whisper Playground
Pull Request -
State: open - Opened by DheerajQblocks 7 months ago
#48 - Online demo is down
Issue -
State: open - Opened by samueldashadrach 8 months ago
- 1 comment
#47 - BEST DIART PARAMETERS IN GENERAL TO USE FOR BETTER DIARIZATION RESULTS
Issue -
State: open - Opened by shanky100 about 1 year ago
#46 - Implement parameter validation in the client
Issue -
State: closed - Opened by ethanzrd about 1 year ago
#45 - Status bar + minor changes
Pull Request -
State: closed - Opened by ethanzrd about 1 year ago
- 1 comment
#44 - Implement status bar
Issue -
State: closed - Opened by ethanzrd about 1 year ago
#43 - Moving the backend's IP into config.js
Issue -
State: closed - Opened by saharmor about 1 year ago
#42 - USING THIS SETUP ON CPU
Issue -
State: open - Opened by shanky100 about 1 year ago
- 14 comments
#41 - Implement multi-client support
Issue -
State: open - Opened by ethanzrd about 1 year ago
#40 - Fix hallucinations + bugfixes
Pull Request -
State: closed - Opened by ethanzrd about 1 year ago
#37 - Implemented error handling for transcription call
Pull Request -
State: closed - Opened by ethanzrd about 1 year ago
#36 - Prevent errors with speechless batches
Issue -
State: closed - Opened by ethanzrd about 1 year ago
#35 - Update README.md
Pull Request -
State: closed - Opened by ethanzrd about 1 year ago
#34 - Error occurred during backend connection.
Issue -
State: closed - Opened by Epresin about 1 year ago
- 5 comments
#33 - Add auto-scroll for transcribed data in client
Issue -
State: closed - Opened by ethanzrd about 1 year ago
#32 - Update client to use localhost for server connection
Pull Request -
State: closed - Opened by ethanzrd about 1 year ago
#31 - Fix incorrect import statements
Pull Request -
State: closed - Opened by ethanzrd about 1 year ago
#30 - The backend is not available on Windows.
Issue -
State: closed - Opened by Epresin about 1 year ago
- 2 comments
Labels: bug
#29 - Modify known bugs and link to issues
Pull Request -
State: closed - Opened by ethanzrd about 1 year ago
#28 - Transcribe the remaining audio data when using the real-time mode
Issue -
State: open - Opened by ethanzrd about 1 year ago
#27 - Manage speakers manually for real-time refinement & avoiding speaker swapping
Issue -
State: open - Opened by ethanzrd about 1 year ago
#26 - Remove redundant steps & improve README.md
Pull Request -
State: closed - Opened by ethanzrd about 1 year ago
- 1 comment
#25 - Add VAD to avoid hallucinations with speechless batches
Issue -
State: closed - Opened by ethanzrd about 1 year ago
#24 - Dockerized the fullstack app
Issue -
State: open - Opened by saharmor over 1 year ago
#23 - Implemented Real-time Audio Transcription with Speaker Diarization
Pull Request -
State: closed - Opened by ethanzrd over 1 year ago
- 2 comments
#21 - Cache model loads (should make subsequent /transcribe calls an order …
Pull Request -
State: open - Opened by kkaehler over 1 year ago
#20 - .... this is for future issues
Issue -
State: closed - Opened by mjund over 1 year ago
#19 - Code switching inputs
Issue -
State: closed - Opened by jayakrishnanmm over 1 year ago
- 1 comment
#18 - I added Dockerfile + proxy for cors issue
Pull Request -
State: open - Opened by perplexedyawdie over 1 year ago
- 4 comments
#17 - Possible to package this in a dockerfile?
Issue -
State: open - Opened by benwhalley over 1 year ago
- 4 comments
#16 - Issue solved
Pull Request -
State: open - Opened by theavitw over 1 year ago
#15 - sh: 1: react-scripts: not found
Issue -
State: open - Opened by developertrinidad08 almost 2 years ago
- 2 comments
#14 - `yarn start` error
Issue -
State: closed - Opened by yubrshen almost 2 years ago
- 6 comments
#13 - How to investigate the problem of "No module named 'flask_cors'"?
Issue -
State: closed - Opened by yubrshen almost 2 years ago
- 1 comment
#11 - Backend error : AttributeError: module 'whisper' has no attribute 'load_model'
Issue -
State: closed - Opened by OK-Cactus almost 2 years ago
- 2 comments
#10 - Use pyannote-audio for speaker diarization
Issue -
State: open - Opened by saharmor almost 2 years ago
- 2 comments
Labels: enhancement, help wanted
#9 - Use whisper.cpp for faster CPU inference
Issue -
State: open - Opened by saharmor almost 2 years ago
Labels: enhancement, help wanted
#8 - WIP Whisper Websocket
Pull Request -
State: open - Opened by chrismbirmingham about 2 years ago
- 2 comments
#7 - Small fixes to whisper_standalone
Pull Request -
State: closed - Opened by chrismbirmingham about 2 years ago
- 3 comments
#6 - Purple dots keep going & no transcription.
Issue -
State: closed - Opened by BrianFenn about 2 years ago
- 7 comments
#4 - Stucking on three purple dots
Issue -
State: closed - Opened by tamto6666 about 2 years ago
- 1 comment
#3 - How to add a new language in the interface?
Issue -
State: closed - Opened by nothingcomeseasy about 2 years ago
- 1 comment
#3 - How to add a new language in the interface?
Issue -
State: closed - Opened by nothingcomeseasy about 2 years ago
- 1 comment
#2 - Pyaudio
Issue -
State: closed - Opened by Alastair1234 about 2 years ago
- 6 comments
#1 - Multiple errors: missing python dev, portaudio and venv
Issue -
State: closed - Opened by Manamama about 2 years ago
- 7 comments