Skip to content

vad : fix memory leaks in VAD implementation #3453

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 6 commits into from
Oct 6, 2025
Merged

vad : fix memory leaks in VAD implementation #3453

Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
aeafca4
vad : fix memory leak by storing ggml_context in vad context struct
danbev Oct 4, 2025
fd95ecc
vad : free memory allocated for VAD hparams
danbev Oct 4, 2025
f3c65a6
vad: free ggml buffer in whisper_vad_free
danbev Oct 4, 2025
a16c662
Revert "vad : fix memory leak by storing ggml_context in vad context …
danbev Oct 6, 2025
46a039a
whisper : free ggml context in whisper_vad_init_context
danbev Oct 6, 2025
36ac9d7
squash! whisper : free ggml context in whisper_vad_init_context
danbev Oct 6, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 7 additions & 0 deletions src/whisper.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4676,6 +4676,7 @@ static bool whisper_vad_init_context(whisper_vad_context * vctx) {
ggml_set_name(vctx->c_state, "c_state");

vctx->buffer = ggml_backend_alloc_ctx_tensors(ctx, vctx->backends[0]);
ggml_free(ctx);
if (!vctx->buffer) {
WHISPER_LOG_ERROR("%s: failed to allocate memory for the VAD state\n", __func__);
return false;
Expand Down Expand Up @@ -5420,6 +5421,9 @@ struct whisper_vad_segments * whisper_vad_segments_from_samples(

void whisper_vad_free(whisper_vad_context * ctx) {
if (ctx) {
if (ctx->buffer) {
ggml_backend_buffer_free(ctx->buffer);
}
for (ggml_context * context : ctx->model.ctxs) {
ggml_free(context);
}
Expand All @@ -5434,6 +5438,9 @@ void whisper_vad_free(whisper_vad_context * ctx) {
ggml_backend_free(backend);
}

delete[] ctx->model.hparams.encoder_in_channels;
delete[] ctx->model.hparams.encoder_out_channels;
delete[] ctx->model.hparams.kernel_sizes;

delete ctx;
}
Expand Down
Loading