Files
whisper.cpp/bindings/ruby/ext/ruby_whisper.h
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

243 lines
6.8 KiB
C

#ifndef RUBY_WHISPER_H
#define RUBY_WHISPER_H
#include <ruby.h>
#include <ruby/version.h>
#include <ruby/util.h>
#include <ruby/thread.h>
#include <ruby/thread_native.h>
#include <ruby/atomic.h>
#include <ruby/memory_view.h>
#include "whisper.h"
#include "parakeet.h"
#include "ruby_whisper_log_settable.h"
#if RUBY_API_VERSION_MAJOR < 4
// Exists but not declared as public API
int ruby_thread_has_gvl_p(void);
#endif
typedef struct {
VALUE *context;
VALUE user_data;
VALUE callback;
VALUE callbacks;
} ruby_whisper_callback_container;
typedef struct ruby_whisper_abort_callback_user_data {
volatile rb_atomic_t is_interrupted;
ruby_whisper_callback_container *callback_container;
} ruby_whisper_abort_callback_user_data;
typedef struct ruby_whisper_log {
enum ggml_log_level level;
char *text;
size_t length;
size_t capacity;
} ruby_whisper_log;
typedef struct ruby_whisper_log_queue {
rb_nativethread_lock_t lock;
rb_nativethread_cond_t cond;
bool is_open;
size_t head;
size_t tail;
size_t size;
ruby_whisper_log *logs;
} ruby_whisper_log_queue;
typedef struct {
struct whisper_context *context;
} ruby_whisper;
typedef struct ruby_whisper_context_params {
struct whisper_context_params params;
} ruby_whisper_context_params;
typedef struct {
struct whisper_full_params params;
bool diarize;
ruby_whisper_callback_container *new_segment_callback_container;
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;
} ruby_whisper_segment;
typedef struct {
whisper_token_data *token_data;
VALUE text;
} ruby_whisper_token;
typedef struct {
VALUE context;
} ruby_whisper_model;
typedef struct {
struct whisper_vad_segments *segments;
} ruby_whisper_vad_segments;
typedef struct {
VALUE segments;
int index;
} ruby_whisper_vad_segment;
typedef struct {
struct whisper_vad_context *context;
} ruby_whisper_vad_context;
typedef struct parsed_samples_t {
float *samples;
int n_samples;
rb_memory_view_t memview;
bool memview_exported;
} parsed_samples_t;
typedef struct {
VALUE *context;
VALUE *params;
float *samples;
int n_samples;
} ruby_whisper_full_args;
typedef struct ruby_whisper_full_parallel_args {
VALUE *context;
VALUE *params;
float *samples;
int n_samples;
int n_processors;
} ruby_whisper_full_parallel_args;
typedef struct {
struct parakeet_full_params params;
ruby_whisper_callback_container *new_segment_callback_container;
ruby_whisper_callback_container *new_token_callback_container;
ruby_whisper_callback_container *progress_callback_container;
ruby_whisper_callback_container *encoder_begin_callback_container;
ruby_whisper_callback_container *abort_callback_container;
} ruby_whisper_parakeet_params;
typedef struct {
struct parakeet_context_params params;
} ruby_whisper_parakeet_context_params;
typedef struct {
struct parakeet_context *context;
} ruby_whisper_parakeet_context;
typedef struct {
VALUE context;
int index;
} ruby_whisper_parakeet_segment;
typedef struct {
parakeet_token_data *token_data;
VALUE text;
} ruby_whisper_parakeet_token;
typedef struct {
VALUE context;
} ruby_whisper_parakeet_model;
extern ID id_extended;
extern ID id_log_callback_thread;
extern ID id_start_log_callback_thread;
extern ID id_alive_p;
extern ID id_join;
extern void ruby_whisper_log_queue_initialize(ruby_whisper_log_queue *log_queue);
extern void ruby_whisper_log_queue_open(ruby_whisper_log_queue *log_queue);
extern void ruby_whisper_log_queue_close(ruby_whisper_log_queue *log_queue);
extern void ruby_whisper_log_queue_enqueue(ruby_whisper_log_queue *log_queue, enum ggml_log_level level, const char *text);
extern VALUE ruby_whisper_log_queue_drain(ruby_whisper_log_queue *log_queue);
#define GetContext(obj, rw) do { \
TypedData_Get_Struct((obj), ruby_whisper, &ruby_whisper_type, (rw)); \
if ((rw)->context == NULL) { \
rb_raise(rb_eRuntimeError, "Not initialized"); \
} \
} while (0)
#define GetContextParams(obj, rwcp) do { \
TypedData_Get_Struct((obj), ruby_whisper_context_params, &ruby_whisper_context_params_type, (rwcp)); \
} while (0)
#define GetToken(obj, rwt) do { \
TypedData_Get_Struct((obj), ruby_whisper_token, &ruby_whisper_token_type, (rwt)); \
if ((rwt)->token_data == NULL) { \
rb_raise(rb_eRuntimeError, "Not initialized"); \
} \
} while (0)
#define GetVADContext(obj, rwvc) do { \
TypedData_Get_Struct((obj), ruby_whisper_vad_context, &ruby_whisper_vad_context_type, (rwvc)); \
if ((rwvc)->context == NULL) { \
rb_raise(rb_eRuntimeError, "Not initialized"); \
} \
} while (0)
#define GetVADParams(obj, rwvp) do { \
TypedData_Get_Struct((obj), ruby_whisper_vad_params, &ruby_whisper_vad_params_type, (rwvp)); \
} while (0)
#define GetVADSegments(obj, rwvss) do { \
TypedData_Get_Struct((obj), ruby_whisper_vad_segments, &ruby_whisper_vad_segments_type, (rwvss)); \
if ((rwvss)->segments == NULL) { \
rb_raise(rb_eRuntimeError, "Not initialized"); \
} \
} while (0)
#define GetParakeetContextParams(obj, rwpcp) do { \
TypedData_Get_Struct((obj), ruby_whisper_parakeet_context_params, &ruby_whisper_parakeet_context_params_type, (rwpcp)); \
} while (0)
#define GetParakeetContext(obj, rwpc) do { \
TypedData_Get_Struct((obj), ruby_whisper_parakeet_context, &ruby_whisper_parakeet_context_type, (rwpc)); \
if ((rwpc)->context == NULL) { \
rb_raise(rb_eRuntimeError, "Not initialized"); \
} \
} while (0)
#define GetParakeetParams(obj, rwpp) do { \
TypedData_Get_Struct((obj), ruby_whisper_parakeet_params, &ruby_whisper_parakeet_params_type, (rwpp)); \
if (!(rwpp)->new_segment_callback_container || \
!(rwpp)->new_token_callback_container || \
!(rwpp)->progress_callback_container || \
!(rwpp)->encoder_begin_callback_container || \
!(rwpp)->abort_callback_container) { \
rb_raise(rb_eRuntimeError, "Not initialized"); \
} \
} while (0)
#define GetParakeetSegment(obj, rwps) do { \
TypedData_Get_Struct((obj), ruby_whisper_parakeet_segment, &ruby_whisper_parakeet_segment_type, (rwps)); \
if (!(rwps)->context) { \
rb_raise(rb_eRuntimeError, "Not initialized"); \
} \
} while (0)
#define GetParakeetToken(obj, rwpt) do { \
TypedData_Get_Struct((obj), ruby_whisper_parakeet_token, &ruby_whisper_parakeet_token_type, (rwpt)); \
if (!(rwpt)->token_data) { \
rb_raise(rb_eRuntimeError, "Not initialized"); \
} \
} while (0)
#define GetParakeetModel(obj, rwpm) do { \
TypedData_Get_Struct((obj), ruby_whisper_parakeet_model, &ruby_whisper_parakeet_model_type, (rwpm)); \
if (NIL_P((rwpm)->context)) { \
rb_raise(rb_eRuntimeError, "Not initialized"); \
} \
} while (0)
#endif