vad : fix memory leaks in VAD implementation (#3453)

* vad : fix memory leak by storing ggml_context in vad context struct

This commit addresses a memory leak issue in the voice activity
detection (VAD) where the ggml_context is not stored within the vad
context structure.

The motivation for this change that this is causing the context memory
to stay allocated and the tensor still point to that memory but this
memory is never freed.

* vad : free memory allocated for VAD hparams

This commit frees the model hyperparameters allocated for the VAD
context in the `whisper_vad_free` function. Specifically, it deletes the
`encoder_in_channels`, `encoder_out_channels`, and `kernel_sizes` arrays
allocated with `new[]` in the `whisper_vad_init` function.

The motivation for this is to prevent memory leaks when the VAD.

* vad: free ggml buffer in whisper_vad_free

This commit frees the ggml buffer in the whisper_vad_free function to
prevent memory leaks.

Resolves: https://github.com/ggml-org/whisper.cpp/issues/3452

* Revert "vad : fix memory leak by storing ggml_context in vad context struct"

This reverts commit aeafca437efa7fb28166703f845e321176aa62ab.

* whisper : free ggml context in whisper_vad_init_context

This commit frees the ggml_context after initializing the VAD context in
the whisper_vad_init_context function.

The motivation for this is to prevent memory leaks.

diff --git a/src/whisper.cpp b/src/whisper.cpp
index d99dd7be68cd8b106ba3dbff36fc5fa1fc0a7a55..39c53ba233ab394b3574dbdbf1c7f39ba7031035 100644 (file)
--- a/src/whisper.cpp
+++ b/src/whisper.cpp
@@ -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;
@@ -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);
         }
@@ -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;
     }