LLM-Inference/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-08-12 22:31:22 +04:00
Code Issues Packages Projects Releases Wiki Activity

whisper : add stateless VAD detect + explicit state reset for streaming (#3677)

Browse Source 
whisper_vad_detect_speech resets LSTM state on every call, which is
correct for batch processing but prevents temporal continuity when
calling per-chunk in a streaming loop.

Add whisper_vad_detect_speech_no_reset (skips buffer clear) and
whisper_vad_reset_state (explicit clear between utterances).
Existing whisper_vad_detect_speech is now a thin wrapper — zero
behavior change for current callers.

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Daniel Worthington-Bodart
2026-04-17 13:36:27 +02:00
committed by GitHub
co-authored by Claude Opus 4.6
parent 95ea8f9bfb
commit 166c20b473
2 changed files with 23 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
include/whisper.h
+10
View File
@@ -695,6 +695,16 @@ extern "C" {
const float * samples,
int n_samples);
// Like whisper_vad_detect_speech, but does not reset LSTM state.
// Use for streaming: call whisper_vad_reset_state() between utterances.
WHISPER_API bool whisper_vad_detect_speech_no_reset(
struct whisper_vad_context * vctx,
const float * samples,
int n_samples);
// Reset LSTM hidden/cell states to zero.
WHISPER_API void whisper_vad_reset_state(struct whisper_vad_context * vctx);
WHISPER_API int whisper_vad_n_probs(struct whisper_vad_context * vctx);
WHISPER_API float * whisper_vad_probs (struct whisper_vad_context * vctx);