mirror of
https://github.com/ggerganov/whisper.cpp.git
synced 2025-06-01 07:25:49 +02:00
* 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
233 lines
6.4 KiB
C
233 lines
6.4 KiB
C
#include <ruby.h>
|
|
#include "ruby_whisper.h"
|
|
|
|
extern const rb_data_type_t ruby_whisper_type;
|
|
|
|
extern VALUE cModel;
|
|
|
|
static void rb_whisper_model_mark(void *p) {
|
|
ruby_whisper_model *rwm = (ruby_whisper_model *)p;
|
|
if (rwm->context) {
|
|
rb_gc_mark(rwm->context);
|
|
}
|
|
}
|
|
|
|
static size_t
|
|
ruby_whisper_model_memsize(const void *p)
|
|
{
|
|
const ruby_whisper_model *rwm = (const ruby_whisper_model *)p;
|
|
size_t size = sizeof(rwm);
|
|
if (!rwm) {
|
|
return 0;
|
|
}
|
|
return size;
|
|
}
|
|
|
|
static const rb_data_type_t rb_whisper_model_type = {
|
|
"ruby_whisper_model",
|
|
{rb_whisper_model_mark, RUBY_DEFAULT_FREE, ruby_whisper_model_memsize,},
|
|
0, 0,
|
|
0
|
|
};
|
|
|
|
static VALUE ruby_whisper_model_allocate(VALUE klass) {
|
|
ruby_whisper_model *rwm;
|
|
return TypedData_Make_Struct(klass, ruby_whisper_model, &rb_whisper_model_type, rwm);
|
|
}
|
|
|
|
VALUE rb_whisper_model_initialize(VALUE context) {
|
|
ruby_whisper_model *rwm;
|
|
const VALUE model = ruby_whisper_model_allocate(cModel);
|
|
TypedData_Get_Struct(model, ruby_whisper_model, &rb_whisper_model_type, rwm);
|
|
rwm->context = context;
|
|
return model;
|
|
};
|
|
|
|
/*
|
|
* call-seq:
|
|
* n_vocab -> Integer
|
|
*/
|
|
static VALUE
|
|
ruby_whisper_model_n_vocab(VALUE self)
|
|
{
|
|
ruby_whisper_model *rwm;
|
|
TypedData_Get_Struct(self, ruby_whisper_model, &rb_whisper_model_type, rwm);
|
|
ruby_whisper *rw;
|
|
TypedData_Get_Struct(rwm->context, ruby_whisper, &ruby_whisper_type, rw);
|
|
return INT2NUM(whisper_model_n_vocab(rw->context));
|
|
}
|
|
|
|
/*
|
|
* call-seq:
|
|
* n_audio_ctx -> Integer
|
|
*/
|
|
static VALUE
|
|
ruby_whisper_model_n_audio_ctx(VALUE self)
|
|
{
|
|
ruby_whisper_model *rwm;
|
|
TypedData_Get_Struct(self, ruby_whisper_model, &rb_whisper_model_type, rwm);
|
|
ruby_whisper *rw;
|
|
TypedData_Get_Struct(rwm->context, ruby_whisper, &ruby_whisper_type, rw);
|
|
return INT2NUM(whisper_model_n_audio_ctx(rw->context));
|
|
}
|
|
|
|
/*
|
|
* call-seq:
|
|
* n_audio_state -> Integer
|
|
*/
|
|
static VALUE
|
|
ruby_whisper_model_n_audio_state(VALUE self)
|
|
{
|
|
ruby_whisper_model *rwm;
|
|
TypedData_Get_Struct(self, ruby_whisper_model, &rb_whisper_model_type, rwm);
|
|
ruby_whisper *rw;
|
|
TypedData_Get_Struct(rwm->context, ruby_whisper, &ruby_whisper_type, rw);
|
|
return INT2NUM(whisper_model_n_audio_state(rw->context));
|
|
}
|
|
|
|
/*
|
|
* call-seq:
|
|
* n_audio_head -> Integer
|
|
*/
|
|
static VALUE
|
|
ruby_whisper_model_n_audio_head(VALUE self)
|
|
{
|
|
ruby_whisper_model *rwm;
|
|
TypedData_Get_Struct(self, ruby_whisper_model, &rb_whisper_model_type, rwm);
|
|
ruby_whisper *rw;
|
|
TypedData_Get_Struct(rwm->context, ruby_whisper, &ruby_whisper_type, rw);
|
|
return INT2NUM(whisper_model_n_audio_head(rw->context));
|
|
}
|
|
|
|
/*
|
|
* call-seq:
|
|
* n_audio_layer -> Integer
|
|
*/
|
|
static VALUE
|
|
ruby_whisper_model_n_audio_layer(VALUE self)
|
|
{
|
|
ruby_whisper_model *rwm;
|
|
TypedData_Get_Struct(self, ruby_whisper_model, &rb_whisper_model_type, rwm);
|
|
ruby_whisper *rw;
|
|
TypedData_Get_Struct(rwm->context, ruby_whisper, &ruby_whisper_type, rw);
|
|
return INT2NUM(whisper_model_n_audio_layer(rw->context));
|
|
}
|
|
|
|
/*
|
|
* call-seq:
|
|
* n_text_ctx -> Integer
|
|
*/
|
|
static VALUE
|
|
ruby_whisper_model_n_text_ctx(VALUE self)
|
|
{
|
|
ruby_whisper_model *rwm;
|
|
TypedData_Get_Struct(self, ruby_whisper_model, &rb_whisper_model_type, rwm);
|
|
ruby_whisper *rw;
|
|
TypedData_Get_Struct(rwm->context, ruby_whisper, &ruby_whisper_type, rw);
|
|
return INT2NUM(whisper_model_n_text_ctx(rw->context));
|
|
}
|
|
|
|
/*
|
|
* call-seq:
|
|
* n_text_state -> Integer
|
|
*/
|
|
static VALUE
|
|
ruby_whisper_model_n_text_state(VALUE self)
|
|
{
|
|
ruby_whisper_model *rwm;
|
|
TypedData_Get_Struct(self, ruby_whisper_model, &rb_whisper_model_type, rwm);
|
|
ruby_whisper *rw;
|
|
TypedData_Get_Struct(rwm->context, ruby_whisper, &ruby_whisper_type, rw);
|
|
return INT2NUM(whisper_model_n_text_state(rw->context));
|
|
}
|
|
|
|
/*
|
|
* call-seq:
|
|
* n_text_head -> Integer
|
|
*/
|
|
static VALUE
|
|
ruby_whisper_model_n_text_head(VALUE self)
|
|
{
|
|
ruby_whisper_model *rwm;
|
|
TypedData_Get_Struct(self, ruby_whisper_model, &rb_whisper_model_type, rwm);
|
|
ruby_whisper *rw;
|
|
TypedData_Get_Struct(rwm->context, ruby_whisper, &ruby_whisper_type, rw);
|
|
return INT2NUM(whisper_model_n_text_head(rw->context));
|
|
}
|
|
|
|
/*
|
|
* call-seq:
|
|
* n_text_layer -> Integer
|
|
*/
|
|
static VALUE
|
|
ruby_whisper_model_n_text_layer(VALUE self)
|
|
{
|
|
ruby_whisper_model *rwm;
|
|
TypedData_Get_Struct(self, ruby_whisper_model, &rb_whisper_model_type, rwm);
|
|
ruby_whisper *rw;
|
|
TypedData_Get_Struct(rwm->context, ruby_whisper, &ruby_whisper_type, rw);
|
|
return INT2NUM(whisper_model_n_text_layer(rw->context));
|
|
}
|
|
|
|
/*
|
|
* call-seq:
|
|
* n_mels -> Integer
|
|
*/
|
|
static VALUE
|
|
ruby_whisper_model_n_mels(VALUE self)
|
|
{
|
|
ruby_whisper_model *rwm;
|
|
TypedData_Get_Struct(self, ruby_whisper_model, &rb_whisper_model_type, rwm);
|
|
ruby_whisper *rw;
|
|
TypedData_Get_Struct(rwm->context, ruby_whisper, &ruby_whisper_type, rw);
|
|
return INT2NUM(whisper_model_n_mels(rw->context));
|
|
}
|
|
|
|
/*
|
|
* call-seq:
|
|
* ftype -> Integer
|
|
*/
|
|
static VALUE
|
|
ruby_whisper_model_ftype(VALUE self)
|
|
{
|
|
ruby_whisper_model *rwm;
|
|
TypedData_Get_Struct(self, ruby_whisper_model, &rb_whisper_model_type, rwm);
|
|
ruby_whisper *rw;
|
|
TypedData_Get_Struct(rwm->context, ruby_whisper, &ruby_whisper_type, rw);
|
|
return INT2NUM(whisper_model_ftype(rw->context));
|
|
}
|
|
|
|
/*
|
|
* call-seq:
|
|
* type -> String
|
|
*/
|
|
static VALUE
|
|
ruby_whisper_model_type(VALUE self)
|
|
{
|
|
ruby_whisper_model *rwm;
|
|
TypedData_Get_Struct(self, ruby_whisper_model, &rb_whisper_model_type, rwm);
|
|
ruby_whisper *rw;
|
|
TypedData_Get_Struct(rwm->context, ruby_whisper, &ruby_whisper_type, rw);
|
|
return rb_str_new2(whisper_model_type_readable(rw->context));
|
|
}
|
|
|
|
void
|
|
init_ruby_whisper_model(VALUE *mWhisper)
|
|
{
|
|
cModel = rb_define_class_under(*mWhisper, "Model", rb_cObject);
|
|
|
|
rb_define_alloc_func(cModel, ruby_whisper_model_allocate);
|
|
rb_define_method(cModel, "n_vocab", ruby_whisper_model_n_vocab, 0);
|
|
rb_define_method(cModel, "n_audio_ctx", ruby_whisper_model_n_audio_ctx, 0);
|
|
rb_define_method(cModel, "n_audio_state", ruby_whisper_model_n_audio_state, 0);
|
|
rb_define_method(cModel, "n_audio_head", ruby_whisper_model_n_audio_head, 0);
|
|
rb_define_method(cModel, "n_audio_layer", ruby_whisper_model_n_audio_layer, 0);
|
|
rb_define_method(cModel, "n_text_ctx", ruby_whisper_model_n_text_ctx, 0);
|
|
rb_define_method(cModel, "n_text_state", ruby_whisper_model_n_text_state, 0);
|
|
rb_define_method(cModel, "n_text_head", ruby_whisper_model_n_text_head, 0);
|
|
rb_define_method(cModel, "n_text_layer", ruby_whisper_model_n_text_layer, 0);
|
|
rb_define_method(cModel, "n_mels", ruby_whisper_model_n_mels, 0);
|
|
rb_define_method(cModel, "ftype", ruby_whisper_model_ftype, 0);
|
|
rb_define_method(cModel, "type", ruby_whisper_model_type, 0);
|
|
}
|