Files
whisper.cpp/bindings/ruby/ext/ruby_whisper_parakeet_segment.c
KITAITI Makoto 0d14756929 ruby : add support for Parakeet (#3885)
* Add Whisper::Parakeet::Params

* Add tests for Parakeet::Params

* Remove unused variabel

* Add callbacks to Parakeet::Params

* Group callback and user_data params

* Undefine local macros

* Define GetParakeetParams

* Remove unused variable

* Use ITERATE_CALLBACK_PARAMS

* Use ITERATE_CALLBACK_PARAMS instead of ITERATE_USER_DATA_PARAMS

* Fix memsize

* Remove unnecessary macros

* Simplify params registration

* Define Parakeet

* Add hook methods to Parakeet::Params

* Fix typo

* Check callback container in GetParakeetParams

* Reduce if

* Free parakeet_full_params

* Implement Parakeet::Context#initialize

* Add TestParakeetContext

* Add Parakeet::Segment

* Prevent double-free

* Add Parakeet::Context#transcribe

* Add Parakeet::Context#each_segment

* Define Parakeet::Segment attributes

* Define Parakeet::Segment#deconstruct_keys

* Add tests for Parakeet::Segment#deconstruct_keys

* Run Parakeet::Context#transcribe without GVL

* Make it to abort for Parakeet

* Add Parakeet.log_set

* Define Parakeet::Token

* Define Parakeet::Segment#each_token

* Implement some hooks of Parakeet::Params

* Convert int to VALUE

* Implement hooks for Parakeet

* Implement Parakeet::Context#full

* Add tests for Parakeet::Context#full

* Add Parakeet to RBS

* Fix ruby_whisper_parakeet_params_free

* Free ruby_whisper_parakeet_context

* Add tests for hooks

* Add Parakeet section to README

* Add more attributes of Parakeet::Context

* Add tests for Parakeet::Context's attributes

* Update RBS

* Register parakeet-tdt-0.6b-v3

* Narrow scope of log constants

* Extract activate and deactivate of log_queue

* Make start_log_callback_thread private

* Don't call start_log_callback_thread unncecessarilly

* Early return from log_queue_enqueue when not active

* Gropu log_queue members

* is_active -> is_open

* Fix English

* Share parakeet full body function

* ruby_whisper_parakeet_abort_callback_user_data -> ruby_whisper_abort_callback_user_data

* NULL check for callback containers

* Fix Parakeet.log_set

* Omit Parakeet tests on CI

* Extract Whisper::LogSettable

* Join log callback thread in a log queue function

* Revert Join log callback thread in a log queue function

* Extract output methods to modules

* Move Parakeet init functions into init_parakeet()

* Add output methods to Parakeet classes

* Add Parakeet's output methods to RBS

* Use Whisper::Output in RBS

* Add LogSettable to RBS

* Fix module Token -> class Token

* Add Parakeet::Model

* Add test for Parakeet::Model

* Add Parakeet::Model to RBS

* Move position of Parakeet::Model in RBS

* Parakeet -> TestBase::Parakeet

* Add Parakeet::Context#model in RBS

* Add Whisper::Output

* Fix nil check

* Define ruby_whisper_parakeet_model_memsize

* Fix order of declaration in ruby_whisper_parakeet_model_get_xxx

* Define Parakeet.system_info_str

* Add test for Parakeet.system_info_str

* Add signature of Parakeet.system_info_str

* Define Parakeet::VERSION

* Add test for Parakeet::VERSION

* Add signature of Parakeet::VERSION

* Add Parakeet::Context::Params

* Make Parakeet::Context.new accept Context::Params

* Add test for Parakeet::Context.new with Context::Params

* Update RBS

* Remove params from Parakeet::Params which are moved from whisper_parakeet_full_params

* Remove tests for removed params

* Make Parakeet tests follow original behavior changes

* Add Parakeet model shortcuts

* Alloc token data in factory instead of alloc func

* Fix variable name

* Update RBS

* Refactor log settable module

* Use log settable for Whisper

* Address deadlock

* Make test follow change of log queue implementation

* Refactor to make abort callback use the same way to parakeet's way

* Remove redundant structs

* Fix test name

* Fix README

* Add missing parallel transcription

* Fix test for parakeet info

* Remove removed params

* Wait for logs dequeued

* Fix instance variable name

* Load etc feature

* Remove unnecessary comment

* Remove unnecessary thread safety check

* Remove outdated comment

* Skip downloading model if cache exists

* Change Hugging Face URI for Parakeet models

* Bump required Ruby version to 3.3

* Fix English
2026-06-17 06:42:09 +02:00

158 lines
4.4 KiB
C

#include "ruby_whisper.h"
#define ITERATE_ATTRS(ITERATOR) \
ITERATOR(start_time, t0, TIME) \
ITERATOR(end_time, t1, TIME) \
ITERATOR(text, text, STRING)
enum {
#define DEF_IDX(name, c_name, type) RUBY_WHISPER_PARAKEET_SEGMENT_##name,
ITERATE_ATTRS(DEF_IDX)
RUBY_WHISPER_PARAKEET_SEGMENT_NUM_ATTRS,
};
#define VAL_FROM_TIME(v) (LONG2NUM((v) * 10))
#define VAL_FROM_STRING(v) (rb_str_new2(v))
#define READER(type) VAL_FROM_##type
#define DEF_ATTR(rb_name, c_name, type) \
static VALUE \
ruby_whisper_parakeet_get_##rb_name(VALUE self) \
{ \
ruby_whisper_parakeet_segment *rwps; \
GetParakeetSegment(self, rwps); \
ruby_whisper_parakeet_context *rwpc; \
GetParakeetContext(rwps->context, rwpc); \
return READER(type)(parakeet_full_get_segment_##c_name(rwpc->context, rwps->index)); \
}
extern ID id___method__;
extern ID id_to_enum;
extern VALUE cParakeetSegment;
extern VALUE sym_start_time;
extern VALUE sym_end_time;
extern VALUE sym_text;
extern const rb_data_type_t ruby_whisper_parakeet_context_type;
extern VALUE ruby_whisper_parakeet_token_s_from_index(struct parakeet_context *context, int i_segment, int i_token);
static void
rb_whisper_parakeet_segment_mark(void *p)
{
ruby_whisper_parakeet_segment *rwps = (ruby_whisper_parakeet_segment *)p;
rb_gc_mark(rwps->context);
}
static size_t
ruby_whisper_parakeet_segment_memsize(const void *p)
{
const ruby_whisper_parakeet_segment *rwps = (const ruby_whisper_parakeet_segment *)p;
if (!rwps) {
return 0;
}
return sizeof(*rwps);
}
static const rb_data_type_t ruby_whisper_parakeet_segment_type = {
"ruby_whisper_parakeet_segment",
{rb_whisper_parakeet_segment_mark, RUBY_DEFAULT_FREE, ruby_whisper_parakeet_segment_memsize,},
0, 0,
0
};
static VALUE
ruby_whisper_parakeet_segment_s_allocate(VALUE klass)
{
ruby_whisper_parakeet_segment *rwps;
return TypedData_Make_Struct(klass, ruby_whisper_parakeet_segment, &ruby_whisper_parakeet_segment_type, rwps);
}
VALUE
ruby_whisper_parakeet_segment_init(VALUE context, int index)
{
ruby_whisper_parakeet_segment *rwps;
const VALUE segment = ruby_whisper_parakeet_segment_s_allocate(cParakeetSegment);
TypedData_Get_Struct(segment, ruby_whisper_parakeet_segment, &ruby_whisper_parakeet_segment_type, rwps);
rwps->context = context;
rwps->index = index;
return segment;
}
ITERATE_ATTRS(DEF_ATTR)
static VALUE
ruby_whisper_parakeet_segment_each_token(VALUE self)
{
if (!rb_block_given_p()) {
const VALUE method_name = rb_funcall(self, id___method__, 0);
return rb_funcall(self, id_to_enum, 1, method_name);
}
ruby_whisper_parakeet_segment *rwps;
GetParakeetSegment(self, rwps);
ruby_whisper_parakeet_context *rwpc;
GetParakeetContext(rwps->context, rwpc);
const int n_tokens = parakeet_full_n_tokens(rwpc->context, rwps->index);
for (int i = 0; i < n_tokens; i++) {
rb_yield(ruby_whisper_parakeet_token_s_from_index(rwpc->context, rwps->index, i));
}
return self;
}
static VALUE
ruby_whisper_parakeet_segment_deconstruct_keys(VALUE self, VALUE keys)
{
ruby_whisper_parakeet_segment *rwps;
GetParakeetSegment(self, rwps);
ruby_whisper_parakeet_context *rwpc;
GetParakeetContext(rwps->context, rwpc);
VALUE hash = rb_hash_new();
long n_keys;
if (NIL_P(keys)) {
keys = rb_ary_new3(
RUBY_WHISPER_PARAKEET_SEGMENT_NUM_ATTRS,
sym_start_time,
sym_end_time,
sym_text
);
n_keys = RUBY_WHISPER_PARAKEET_SEGMENT_NUM_ATTRS;
} else {
n_keys = RARRAY_LEN(keys);
if (n_keys > RUBY_WHISPER_PARAKEET_SEGMENT_NUM_ATTRS) {
return hash;
}
}
for (int i = 0; i < n_keys; i++) {
VALUE key = rb_ary_entry(keys, i);
#define CHECK_AND_SET_KEY(rb_name, c_name, type) \
if (key == sym_##rb_name) { \
rb_hash_aset(hash, key, ruby_whisper_parakeet_get_##rb_name(self)); \
}
ITERATE_ATTRS(CHECK_AND_SET_KEY)
}
return hash;
}
void
init_ruby_whisper_parakeet_segment(VALUE *mParakeet)
{
cParakeetSegment = rb_define_class_under(*mParakeet, "Segment", rb_cObject);
rb_define_alloc_func(cParakeetSegment, ruby_whisper_parakeet_segment_s_allocate);
#define REGISTER_ATTR(rb_name, c_name, type) \
rb_define_method(cParakeetSegment, #rb_name, ruby_whisper_parakeet_get_##rb_name, 0);
ITERATE_ATTRS(REGISTER_ATTR)
rb_define_method(cParakeetSegment, "each_token", ruby_whisper_parakeet_segment_each_token, 0);
rb_define_method(cParakeetSegment, "deconstruct_keys", ruby_whisper_parakeet_segment_deconstruct_keys, 1);
}