]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
vad : add initial Voice Activity Detection (VAD) support (#3065)
authorDaniel Bevenius <redacted>
Mon, 12 May 2025 14:10:11 +0000 (16:10 +0200)
committerGitHub <redacted>
Mon, 12 May 2025 14:10:11 +0000 (16:10 +0200)
commite41bc5c61ae66af6be2bd7011769bb821a83e8ae
treef35b1e23516f8df781e036976a3363b752b7d781
parente39ba750cdcaf5a587ccb5d38fdc3227d3096066
vad : add initial Voice Activity Detection (VAD) support (#3065)

* 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 <redacted>
.github/workflows/build.yml
README.md
examples/cli/cli.cpp
include/whisper.h
models/convert-silero-vad-to-ggml.py [new file with mode: 0644]
models/for-tests-silero-v5.1.2-ggml.bin [new file with mode: 0644]
src/whisper-arch.h
src/whisper.cpp
tests/CMakeLists.txt
tests/test-vad-full.cpp [new file with mode: 0644]
tests/test-vad.cpp [new file with mode: 0644]