| Commit message (Collapse) | Author | Age |
|---|
| |
|
|
| |
No longer used.
|
| |
|
|
|
|
| |
This is a much faster, lower-VRAM reimplementation of Whisper in Python.
Early testing is extremely promising: fast transcription speed,
extremely low resource usage (CPU/RAM/VRAM), high accuracy.
|
| |
|
|
|
| |
Need python310._pth, specifically 'import site' line, for
embedded python + pip to get along.
|
| |
|
|
|
|
|
|
| |
Expose decode method, beam search parameters, and voice activity
detection parameters in GUI.
* Remove WhisperCPP::Init(), do it on launch instead.
* Add float support to ConfigMarshal
|
| |
|
|
|
|
| |
Do these in a std::future.
* SetAffinityMask() now returns a value on all control paths
|
| |
|
|
|
| |
* Plumb beam search params into whisper cpp implementation
(currently broken)
|
|
|
Use forked Whisper implementation which has tweaks to reduce dropped
words around the beginning VAD segments.
* Retain audio after VAD segmentation events
|
