Release v1.3.18.10 · Sharrnah/whispering (original) (raw)

Important:

This requires a lot of configuration if run directly. Recommended way is to use UI Application: https://github.com/Sharrnah/whispering-ui which downloads this automatically.

Standalone Release File (4.7 GB):

Download Server:

• EU: https://eu2.contabostorage.com/bf1a89517e2643359087e5d8219c0c67:projects/whispering/whispering-tiger1.3.18.10_win.zip
• US: https://usc1.contabostorage.com/8fcf133c506f4e688c7ab9ad537b5c18:projects/whispering/whispering-tiger1.3.18.10_win.zip

Changelog (v1.3.18.10)

• [FEATURE] Add NeMo Canary v2 model
• [TASK] Chatterbox + kokoro - unify tts segment generation
• [TASK] Improve segment streaming in chatterbox
• [TASK] Add class to write PCM Raw wav with header
• [TASK] Add progress display over all segments
• [TASK] Update dependencies
• [BUGFIX] Speaker diarization error on non-nvidia hardware
• [BUGFIX] Loading Seamless M4T
• [BUGFIX] Send transcriptions over Websocket even if OSC is disabled
• [BUGFIX] Correctly show (OSC) in log when OSC is active only
• [BUGFIX] Implement workaround for chatterbox slowdown over time
• [BUGFIX] write temp file for nemo canary models

Full Changelog: v1.3.18.9...v1.3.18.10