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

200 lines
6.8 KiB
C

#include "ruby_whisper.h"
VALUE mWhisper;
VALUE mLogSettable;
VALUE mVAD;
VALUE mParakeet;
VALUE cContext;
VALUE cParams;
VALUE cVADContext;
VALUE cVADParams;
VALUE cVADSegments;
VALUE cVADSegment;
VALUE cParakeetContext;
VALUE cParakeetContextParams;
VALUE cParakeetParams;
VALUE cParakeetSegment;
VALUE cParakeetModel;
VALUE eError;
VALUE cSegment;
VALUE cToken;
VALUE cModel;
VALUE mOutputContext;
VALUE mOutputSegment;
ID id_to_s;
ID id_call;
ID id___method__;
ID id_to_enum;
ID id_length;
ID id_next;
ID id_new;
ID id_to_path;
ID id_URI;
ID id_pre_converted_models;
ID id_coreml_compiled_models;
ID id_cache;
ID id_n_processors;
ID id_extended;
ID id_start_log_callback_thread;
ID id_log_callback_thread;
ID id_alive_p;
ID id_join;
// High level API
extern VALUE ruby_whisper_segment_allocate(VALUE klass);
extern VALUE init_ruby_whisper_context(VALUE *mWhisper);
extern void init_ruby_whisper_context_params(VALUE *cContext);
extern void init_ruby_whisper_params(VALUE *mWhisper);
extern void init_ruby_whisper_error(VALUE *mWhisper);
extern void init_ruby_whisper_segment(VALUE *mWhisper);
extern void init_ruby_whisper_token(VALUE *mWhisper);
extern void init_ruby_whisper_model(VALUE *mWhisper);
extern void init_ruby_whisper_vad_params(VALUE *mVAD);
extern void init_ruby_whisper_vad_context(VALUE *mVAD);
extern void init_ruby_whisper_vad_segment(VALUE *mVAD);
extern void init_ruby_whisper_vad_segments(VALUE *mVAD);
extern void init_ruby_whisper_parakeet(VALUE *mWhisper);
extern void register_callbacks(ruby_whisper_params *rwp, VALUE *context);
static ruby_whisper_log_queue whisper_log_queue;
LOG_SETTABLE_SETUP(whisper_log_queue, mWhisper, whisper_log_set)
/*
* call-seq:
* lang_max_id -> Integer
*/
static VALUE ruby_whisper_s_lang_max_id(VALUE self) {
return INT2NUM(whisper_lang_max_id());
}
/*
* call-seq:
* lang_id(lang_name) -> Integer
*/
static VALUE ruby_whisper_s_lang_id(VALUE self, VALUE lang) {
const char * lang_str = StringValueCStr(lang);
const int id = whisper_lang_id(lang_str);
if (-1 == id) {
rb_raise(rb_eArgError, "language not found: %s", lang_str);
}
return INT2NUM(id);
}
/*
* call-seq:
* lang_str(lang_id) -> String
*/
static VALUE ruby_whisper_s_lang_str(VALUE self, VALUE id) {
const int lang_id = NUM2INT(id);
const char * str = whisper_lang_str(lang_id);
if (NULL == str) {
rb_raise(rb_eIndexError, "id %d outside of language id", lang_id);
}
return rb_str_new2(str);
}
/*
* call-seq:
* lang_str(lang_id) -> String
*/
static VALUE ruby_whisper_s_lang_str_full(VALUE self, VALUE id) {
const int lang_id = NUM2INT(id);
const char * str_full = whisper_lang_str_full(lang_id);
if (NULL == str_full) {
rb_raise(rb_eIndexError, "id %d outside of language id", lang_id);
}
return rb_str_new2(str_full);
}
/*
* call-seq:
* system_info_str -> String
*/
static VALUE ruby_whisper_s_system_info_str(VALUE self) {
return rb_str_new2(whisper_print_system_info());
}
void Init_whisper() {
id_to_s = rb_intern("to_s");
id_call = rb_intern("call");
id___method__ = rb_intern("__method__");
id_to_enum = rb_intern("to_enum");
id_length = rb_intern("length");
id_next = rb_intern("next");
id_new = rb_intern("new");
id_to_path = rb_intern("to_path");
id_URI = rb_intern("URI");
id_pre_converted_models = rb_intern("pre_converted_models");
id_coreml_compiled_models = rb_intern("coreml_compiled_models");
id_cache = rb_intern("cache");
id_n_processors = rb_intern("n_processors");
id_extended = rb_intern("extended");
id_start_log_callback_thread = rb_intern("start_log_callback_thread");
id_log_callback_thread = rb_intern("@log_callback_thread");
id_alive_p = rb_intern("alive?");
id_join = rb_intern("join");
mWhisper = rb_define_module("Whisper");
rb_require("whisper/log_settable");
mLogSettable = rb_path2class("Whisper::LogSettable");
mVAD = rb_define_module_under(mWhisper, "VAD");
rb_require("whisper/output");
mOutputContext = rb_path2class("Whisper::Output::Context");
mOutputSegment = rb_path2class("Whisper::Output::Segment");
rb_define_const(mWhisper, "VERSION", rb_str_new2(whisper_version()));
rb_define_const(mWhisper, "LOG_LEVEL_NONE", INT2NUM(GGML_LOG_LEVEL_NONE));
rb_define_const(mWhisper, "LOG_LEVEL_INFO", INT2NUM(GGML_LOG_LEVEL_INFO));
rb_define_const(mWhisper, "LOG_LEVEL_WARN", INT2NUM(GGML_LOG_LEVEL_WARN));
rb_define_const(mWhisper, "LOG_LEVEL_ERROR", INT2NUM(GGML_LOG_LEVEL_ERROR));
rb_define_const(mWhisper, "LOG_LEVEL_DEBUG", INT2NUM(GGML_LOG_LEVEL_DEBUG));
rb_define_const(mWhisper, "LOG_LEVEL_CONT", INT2NUM(GGML_LOG_LEVEL_CONT));
rb_define_const(mWhisper, "AHEADS_NONE", INT2NUM(WHISPER_AHEADS_NONE));
rb_define_const(mWhisper, "AHEADS_N_TOP_MOST", INT2NUM(WHISPER_AHEADS_N_TOP_MOST));
rb_define_const(mWhisper, "AHEADS_CUSTOM", INT2NUM(WHISPER_AHEADS_CUSTOM));
rb_define_const(mWhisper, "AHEADS_TINY_EN", INT2NUM(WHISPER_AHEADS_TINY_EN));
rb_define_const(mWhisper, "AHEADS_TINY", INT2NUM(WHISPER_AHEADS_TINY));
rb_define_const(mWhisper, "AHEADS_BASE_EN", INT2NUM(WHISPER_AHEADS_BASE_EN));
rb_define_const(mWhisper, "AHEADS_BASE", INT2NUM(WHISPER_AHEADS_BASE));
rb_define_const(mWhisper, "AHEADS_SMALL_EN", INT2NUM(WHISPER_AHEADS_SMALL_EN));
rb_define_const(mWhisper, "AHEADS_SMALL", INT2NUM(WHISPER_AHEADS_SMALL));
rb_define_const(mWhisper, "AHEADS_MEDIUM_EN", INT2NUM(WHISPER_AHEADS_MEDIUM_EN));
rb_define_const(mWhisper, "AHEADS_MEDIUM", INT2NUM(WHISPER_AHEADS_MEDIUM));
rb_define_const(mWhisper, "AHEADS_LARGE_V1", INT2NUM(WHISPER_AHEADS_LARGE_V1));
rb_define_const(mWhisper, "AHEADS_LARGE_V2", INT2NUM(WHISPER_AHEADS_LARGE_V2));
rb_define_const(mWhisper, "AHEADS_LARGE_V3", INT2NUM(WHISPER_AHEADS_LARGE_V3));
rb_define_const(mWhisper, "AHEADS_LARGE_V3_TURBO", INT2NUM(WHISPER_AHEADS_LARGE_V3_TURBO));
rb_define_singleton_method(mWhisper, "lang_max_id", ruby_whisper_s_lang_max_id, 0);
rb_define_singleton_method(mWhisper, "lang_id", ruby_whisper_s_lang_id, 1);
rb_define_singleton_method(mWhisper, "lang_str", ruby_whisper_s_lang_str, 1);
rb_define_singleton_method(mWhisper, "lang_str_full", ruby_whisper_s_lang_str_full, 1);
rb_define_singleton_method(mWhisper, "system_info_str", ruby_whisper_s_system_info_str, 0);
LOG_SETTABLE_INIT(whisper_log_queue, mWhisper)
cContext = init_ruby_whisper_context(&mWhisper);
init_ruby_whisper_context_params(&cContext);
init_ruby_whisper_params(&mWhisper);
init_ruby_whisper_error(&mWhisper);
init_ruby_whisper_segment(&mWhisper);
init_ruby_whisper_token(&mWhisper);
init_ruby_whisper_model(&mWhisper);
init_ruby_whisper_vad_params(&mVAD);
init_ruby_whisper_vad_segment(&mVAD);
init_ruby_whisper_vad_segments(&mVAD);
init_ruby_whisper_vad_context(&mVAD);
init_ruby_whisper_parakeet(&mWhisper);
rb_require("whisper/model/uri");
rb_include_module(cContext, mOutputContext);
rb_include_module(cSegment, mOutputSegment);
}