ruby : add VAD support, migration to Ruby's newer API (#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
This commit is contained in:
KITAITI Makoto
2025-05-28 20:05:12 +09:00
committed by GitHub
parent 5720426d97
commit 1f5fdbecb4
14 changed files with 925 additions and 173 deletions

View File

@ -1,20 +1,40 @@
#include <ruby.h>
#include "ruby_whisper.h"
extern const rb_data_type_t ruby_whisper_type;
extern VALUE cSegment;
static void
rb_whisper_segment_mark(ruby_whisper_segment *rws)
rb_whisper_segment_mark(void *p)
{
ruby_whisper_segment *rws = (ruby_whisper_segment *)p;
rb_gc_mark(rws->context);
}
static size_t
ruby_whisper_segment_memsize(const void *p)
{
const ruby_whisper_segment *rws = (const ruby_whisper_segment *)p;
size_t size = sizeof(rws);
if (!rws) {
return 0;
}
return size;
}
static const rb_data_type_t ruby_whisper_segment_type = {
"ruby_whisper_segment",
{rb_whisper_segment_mark, RUBY_DEFAULT_FREE, ruby_whisper_segment_memsize,},
0, 0,
0
};
VALUE
ruby_whisper_segment_allocate(VALUE klass)
{
ruby_whisper_segment *rws;
rws = ALLOC(ruby_whisper_segment);
return Data_Wrap_Struct(klass, rb_whisper_segment_mark, RUBY_DEFAULT_FREE, rws);
return TypedData_Make_Struct(klass, ruby_whisper_segment, &ruby_whisper_segment_type, rws);
}
VALUE
@ -22,7 +42,7 @@ rb_whisper_segment_initialize(VALUE context, int index)
{
ruby_whisper_segment *rws;
const VALUE segment = ruby_whisper_segment_allocate(cSegment);
Data_Get_Struct(segment, ruby_whisper_segment, rws);
TypedData_Get_Struct(segment, ruby_whisper_segment, &ruby_whisper_segment_type, rws);
rws->context = context;
rws->index = index;
return segment;
@ -38,9 +58,9 @@ static VALUE
ruby_whisper_segment_get_start_time(VALUE self)
{
ruby_whisper_segment *rws;
Data_Get_Struct(self, ruby_whisper_segment, rws);
TypedData_Get_Struct(self, ruby_whisper_segment, &ruby_whisper_segment_type, rws);
ruby_whisper *rw;
Data_Get_Struct(rws->context, ruby_whisper, rw);
TypedData_Get_Struct(rws->context, ruby_whisper, &ruby_whisper_type, rw);
const int64_t t0 = whisper_full_get_segment_t0(rw->context, rws->index);
// able to multiply 10 without overflow because to_timestamp() in whisper.cpp does it
return INT2NUM(t0 * 10);
@ -56,9 +76,9 @@ static VALUE
ruby_whisper_segment_get_end_time(VALUE self)
{
ruby_whisper_segment *rws;
Data_Get_Struct(self, ruby_whisper_segment, rws);
TypedData_Get_Struct(self, ruby_whisper_segment, &ruby_whisper_segment_type, rws);
ruby_whisper *rw;
Data_Get_Struct(rws->context, ruby_whisper, rw);
TypedData_Get_Struct(rws->context, ruby_whisper, &ruby_whisper_type, rw);
const int64_t t1 = whisper_full_get_segment_t1(rw->context, rws->index);
// able to multiply 10 without overflow because to_timestamp() in whisper.cpp does it
return INT2NUM(t1 * 10);
@ -74,9 +94,9 @@ static VALUE
ruby_whisper_segment_get_speaker_turn_next(VALUE self)
{
ruby_whisper_segment *rws;
Data_Get_Struct(self, ruby_whisper_segment, rws);
TypedData_Get_Struct(self, ruby_whisper_segment, &ruby_whisper_segment_type, rws);
ruby_whisper *rw;
Data_Get_Struct(rws->context, ruby_whisper, rw);
TypedData_Get_Struct(rws->context, ruby_whisper, &ruby_whisper_type, rw);
return whisper_full_get_segment_speaker_turn_next(rw->context, rws->index) ? Qtrue : Qfalse;
}
@ -88,9 +108,9 @@ static VALUE
ruby_whisper_segment_get_text(VALUE self)
{
ruby_whisper_segment *rws;
Data_Get_Struct(self, ruby_whisper_segment, rws);
TypedData_Get_Struct(self, ruby_whisper_segment, &ruby_whisper_segment_type, rws);
ruby_whisper *rw;
Data_Get_Struct(rws->context, ruby_whisper, rw);
TypedData_Get_Struct(rws->context, ruby_whisper, &ruby_whisper_type, rw);
const char * text = whisper_full_get_segment_text(rw->context, rws->index);
return rb_str_new2(text);
}
@ -103,9 +123,9 @@ static VALUE
ruby_whisper_segment_get_no_speech_prob(VALUE self)
{
ruby_whisper_segment *rws;
Data_Get_Struct(self, ruby_whisper_segment, rws);
TypedData_Get_Struct(self, ruby_whisper_segment, &ruby_whisper_segment_type, rws);
ruby_whisper *rw;
Data_Get_Struct(rws->context, ruby_whisper, rw);
TypedData_Get_Struct(rws->context, ruby_whisper, &ruby_whisper_type, rw);
return DBL2NUM(whisper_full_get_segment_no_speech_prob(rw->context, rws->index));
}