Files
whisper.cpp/bindings/ruby/ext/ruby_whisper_vad_segment.c
KITAITI Makoto 97c56f1dc1 ruby : add VAD speech segments API (#3931)
* Bump version

* Add test for VAD segments API

* Implement VAD segments API

* Add signatures of VAD segments API

* Stop to dependent on mutex_m

* Check segment range for vad_segment_t0/t1

* Remove needless check

* Remove dead codes

* Fix index check for VAD segments

* Remove needless line

* Use NUM2DBL instead of RFLOAT_VALUE for safety

* Fix document

* Check type of samples

* Arrange CMake cache notation for older version

* Remove unnecessary line break

* Check return value of whisper_vad_segments_from_samples

* Fix type of VAD::Segment#start_time and #end_time

* Prevent dangling pointer from Params to VAD::Params

* Fix typos

* Update README

* Make test follow fix of impl

* Use segments_from_samples_body in ruby_whisper_vad_detect

* Run segments_from_samples without GVL

* Remove unnecessary codes

* [skip ci]Remove trailing whitespace

Co-authored-by: Daniel Bevenius <daniel.bevenius@gmail.com>

---------

Co-authored-by: Daniel Bevenius <daniel.bevenius@gmail.com>
2026-07-28 15:08:44 +09:00

139 lines
3.8 KiB
C

#include "ruby_whisper.h"
#define N_KEY_NAMES 2
extern VALUE cVADSegment;
extern const rb_data_type_t ruby_whisper_vad_segments_type;
static VALUE sym_start_time;
static VALUE sym_end_time;
static void
rb_whisper_vad_segment_mark(void *p)
{
ruby_whisper_vad_segment *rwvs = (ruby_whisper_vad_segment *)p;
rb_gc_mark(rwvs->segments);
}
static size_t
ruby_whisper_vad_segment_memsize(const void *p)
{
const ruby_whisper_vad_segment *rwvs = p;
size_t size = sizeof(rwvs);
if (!rwvs) {
return 0;
}
if (rwvs->index) {
size += sizeof(rwvs->index);
}
return size;
}
static const rb_data_type_t ruby_whisper_vad_segment_type = {
"ruby_whisper_vad_segment",
{rb_whisper_vad_segment_mark, RUBY_DEFAULT_FREE, ruby_whisper_vad_segment_memsize,},
0, 0,
0
};
static VALUE
ruby_whisper_vad_segment_s_allocate(VALUE klass)
{
ruby_whisper_vad_segment *rwvs;
VALUE obj = TypedData_Make_Struct(klass, ruby_whisper_vad_segment, &ruby_whisper_vad_segment_type, rwvs);
rwvs->segments = Qnil;
rwvs->index = -1;
return obj;
}
VALUE
rb_whisper_vad_segment_s_new(VALUE segments, int index)
{
ruby_whisper_vad_segment *rwvs;
const VALUE segment = ruby_whisper_vad_segment_s_allocate(cVADSegment);
TypedData_Get_Struct(segment, ruby_whisper_vad_segment, &ruby_whisper_vad_segment_type, rwvs);
rwvs->segments = segments;
rwvs->index = index;
return segment;
}
static VALUE
ruby_whisper_vad_segment_get_start_time(VALUE self)
{
ruby_whisper_vad_segment *rwvs;
ruby_whisper_vad_segments *rwvss;
float t0;
TypedData_Get_Struct(self, ruby_whisper_vad_segment, &ruby_whisper_vad_segment_type, rwvs);
TypedData_Get_Struct(rwvs->segments, ruby_whisper_vad_segments, &ruby_whisper_vad_segments_type, rwvss);
t0 = whisper_vad_segments_get_segment_t0(rwvss->segments, rwvs->index);
return LONG2NUM(t0 * 10);
}
static VALUE
ruby_whisper_vad_segment_get_end_time(VALUE self)
{
ruby_whisper_vad_segment *rwvs;
ruby_whisper_vad_segments *rwvss;
float t1;
TypedData_Get_Struct(self, ruby_whisper_vad_segment, &ruby_whisper_vad_segment_type, rwvs);
TypedData_Get_Struct(rwvs->segments, ruby_whisper_vad_segments, &ruby_whisper_vad_segments_type, rwvss);
t1 = whisper_vad_segments_get_segment_t1(rwvss->segments, rwvs->index);
return LONG2NUM(t1 * 10);
}
static VALUE
ruby_whisper_vad_segment_deconstruct_keys(VALUE self, VALUE keys)
{
ruby_whisper_vad_segment *rwvs;
ruby_whisper_vad_segments *rwvss;
VALUE hash, key;
long n_keys;
int i;
TypedData_Get_Struct(self, ruby_whisper_vad_segment, &ruby_whisper_vad_segment_type, rwvs);
TypedData_Get_Struct(rwvs->segments, ruby_whisper_vad_segments, &ruby_whisper_vad_segments_type, rwvss);
hash = rb_hash_new();
if (NIL_P(keys)) {
keys = rb_ary_new3(
N_KEY_NAMES,
sym_start_time,
sym_end_time
);
n_keys = N_KEY_NAMES;
} else {
n_keys = RARRAY_LEN(keys);
if (n_keys > N_KEY_NAMES) {
return hash;
}
}
for (i = 0; i < n_keys; i++) {
key = rb_ary_entry(keys, i);
if (key == sym_start_time) {
rb_hash_aset(hash, key, ruby_whisper_vad_segment_get_start_time(self));
}
if (key == sym_end_time) {
rb_hash_aset(hash, key, ruby_whisper_vad_segment_get_end_time(self));
}
}
return hash;
}
void
init_ruby_whisper_vad_segment(VALUE *mVAD)
{
cVADSegment = rb_define_class_under(*mVAD, "Segment", rb_cObject);
sym_start_time = ID2SYM(rb_intern("start_time"));
sym_end_time = ID2SYM(rb_intern("end_time"));
rb_define_alloc_func(cVADSegment, ruby_whisper_vad_segment_s_allocate);
rb_define_method(cVADSegment, "start_time", ruby_whisper_vad_segment_get_start_time, 0);
rb_define_method(cVADSegment, "end_time", ruby_whisper_vad_segment_get_end_time, 0);
rb_define_method(cVADSegment, "deconstruct_keys", ruby_whisper_vad_segment_deconstruct_keys, 1);
}