ruby : add VAD support, migration to Ruby's newer API (ggml-org#3197)

* Add VAD models

* Extract function to normalize model path from ruby_whisper_initialize()

* Define ruby_whisper_vad_params struct

* Add VAD-related features to Whisper::Params

* Add tests for VAD-related features

* Define Whisper::VADParams

* Add Whisper::VAD::Params attributes

* Add test suite for VAD::Params

* Make older test to follow namespace change

* Add test for transcription with VAD

* Add assertion for test_vad_params

* Add signatures for VAD-related methods

* Define VAD::Params#==

* Add test for VAD::Params#==

* Fix Params#vad_params

* Add test for Params#vad_params

* Fix signature of Params#vad_params

* Use macro to define VAD::Params params

* Define VAD::Params#initialize

* Add tests for VAD::Params#initialize

* Add signature for VAD::Params.new

* Add documentation on VAD in README

* Wrap register_callbask in prepare_transcription for clear meanings

* Set whisper_params.vad_params just before transcription

* Don't touch NULL

* Define ruby_whisper_params_type

* Use TypedData_XXX for ruby_whisper_params instead of Data_XXX

* Remove unused functions

* Define rb_whisper_model_data_type

* Use TypedData_XXX for ruby_whisper_model instead of Data_XXX

* Define ruby_whisper_segment_type

* Use TypedData_XXX for ruby_whisper_segment instead of Data_XXX

* Define ruby_whisper_type

* Use TypedData_XXX for ruby_whisper instead of Data_XXX

* Qualify with const

Author: KitaitiMakoto

bindings/ruby/README.md

@@ -111,6 +111,41 @@ See [models][] page for details.
 
 Currently, whisper.cpp accepts only 16-bit WAV files.
 
+### Voice Activity Detection (VAD) ###
+
+Support for Voice Activity Detection (VAD) can be enabled by setting `Whisper::Params`'s `vad` argument to `true` and specifying VAD model:
+
+```ruby
+Whisper::Params.new(
+  vad: true,
+  vad_model_path: "silero-v5.1.2",
+  # other arguments...
+)
+```
+
+When you pass the model name (`"silero-v5.1.2"`) or URI (`https://huggingface.co/ggml-org/whisper-vad/resolve/main/ggml-silero-v5.1.2.bin`), it will be downloaded automatically.
+Currently, "silero-v5.1.2" is registered as pre-converted model like ASR models. You also specify file path or URI of model.
+
+If you need configure VAD behavior, pass params for that:
+
+```ruby
+Whisper::Params.new(
+  vad: true,
+  vad_model_path: "silero-v5.1.2",
+  vad_params: Whisper::VAD::Params.new(
+    threshold: 1.0, # defaults to 0.5
+    min_speech_duration_ms: 500, # defaults to 250
+    min_silence_duration_ms: 200, # defaults to 100
+    max_speech_duration_s: 30000, # default is FLT_MAX,
+    speech_pad_ms: 50, # defaults to 30
+    samples_overlap: 0.5 # defaults to 0.1
+  ),
+  # other arguments...
+)
+```
+
+For details on VAD, see [whisper.cpp's README](https://github.com/ggml-org/whisper.cpp?tab=readme-ov-file#voice-activity-detection-vad).
+
 API
 ---
 

bindings/ruby/ext/ruby_whisper.c

@@ -3,8 +3,10 @@
 #include "ruby_whisper.h"
 
 VALUE mWhisper;
+VALUE mVAD;
 VALUE cContext;
 VALUE cParams;
+VALUE cVADParams;
 VALUE eError;
 
 VALUE cSegment;
@@ -31,6 +33,7 @@ extern void init_ruby_whisper_params(VALUE *mWhisper);
 extern void init_ruby_whisper_error(VALUE *mWhisper);
 extern void init_ruby_whisper_segment(VALUE *mWhisper, VALUE *cSegment);
 extern void init_ruby_whisper_model(VALUE *mWhisper);
+extern void init_ruby_whisper_vad_params(VALUE *mVAD);
 extern void register_callbacks(ruby_whisper_params *rwp, VALUE *context);
 
 /*
@@ -116,16 +119,6 @@ static VALUE ruby_whisper_s_log_set(VALUE self, VALUE log_callback, VALUE user_d
   return Qnil;
 }
 
-static void rb_whisper_model_mark(ruby_whisper_model *rwm) {
-  rb_gc_mark(rwm->context);
-}
-
-static VALUE ruby_whisper_model_allocate(VALUE klass) {
-  ruby_whisper_model *rwm;
-  rwm = ALLOC(ruby_whisper_model);
-  return Data_Wrap_Struct(klass, rb_whisper_model_mark, RUBY_DEFAULT_FREE, rwm);
-}
-
 void Init_whisper() {
   id_to_s = rb_intern("to_s");
   id_call = rb_intern("call");
@@ -139,6 +132,7 @@ void Init_whisper() {
   id_pre_converted_models = rb_intern("pre_converted_models");
 
   mWhisper = rb_define_module("Whisper");
+  mVAD = rb_define_module_under(mWhisper, "VAD");
 
   rb_define_const(mWhisper, "LOG_LEVEL_NONE", INT2NUM(GGML_LOG_LEVEL_NONE));
   rb_define_const(mWhisper, "LOG_LEVEL_INFO", INT2NUM(GGML_LOG_LEVEL_INFO));
@@ -159,6 +153,7 @@ void Init_whisper() {
   init_ruby_whisper_error(&mWhisper);
   init_ruby_whisper_segment(&mWhisper, &cContext);
   init_ruby_whisper_model(&mWhisper);
+  init_ruby_whisper_vad_params(&mVAD);
 
   rb_require("whisper/model/uri");
 }

bindings/ruby/ext/ruby_whisper.h

@@ -21,8 +21,13 @@ typedef struct {
   ruby_whisper_callback_container *progress_callback_container;
   ruby_whisper_callback_container *encoder_begin_callback_container;
   ruby_whisper_callback_container *abort_callback_container;
+  VALUE vad_params;
 } ruby_whisper_params;
 
+typedef struct {
+  struct whisper_vad_params params;
+} ruby_whisper_vad_params;
+
 typedef struct {
   VALUE context;
   int index;