When processing long audio, whisper tends to produce progressively
shorter segments because timestamp tokens in the decoder prompt context
condition the model to insert more frequent segment breaks.
Add a seg_len_hint parameter (in ms) that thins timestamp tokens in
the rolling prompt context, keeping at most one per seg_len_hint
interval. This breaks the feedback loop while preserving text tokens
for continuity. The model can still break on natural boundaries
(speaker turns, pauses) — the hint only affects context conditioning,
not the actual segment creation.
Usage: --seg-len-hint 2000 (for ~2 second target segments)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* Add support for --carry-initial-prompt
* PR fixes for ruby and go
* Refactoring for readability
* WIP 1
* WIP 2
* PR fixes
* More PR fixes
* PR fix
* Further simplification
* d'oh
* One more logic fix
* Update src/whisper.cpp
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Truncate prompt_past0 upon initialization
* Slight simplification
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* whisper : add version function
This commit adds a version function to the whisper API.
The motivation for this is that it might be convenient to have a way to
programmatically check the version.
Example usage:
```c++
printf("Using whisper version: %s\n", whisper_version());
```
Will output:
```console
Using whisper version: 1.7.6
```
* examples : add version to android example CMakeLists.txt
* vad : add initial Voice Activity Detection (VAD) support
This commit add support for Voice Activity Detection (VAD). When enabled
this feature will process the audio input and detect speech segments.
This information is then used to reduce the number of samples that need
to be processed by whisper_full.
Resolves: https://github.com/ggml-org/whisper.cpp/issues/3003
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Fixed OpenVino init on state
* Removed an empty line
* Fixed typo
* Replaced tabs with spaces
---------
Co-authored-by: Sandro Hanea <sandrohanea@users.noreply.github.com>
Liz Fong-Jones
Andreas Lubbe
Daniel Bevenius
Sandro Hanea
Sacha Arbonel
Georgi Gerganov
Karthick
Jhen-Jie Hong
Rotem Dan