Files
whisper.cpp/bindings/ruby/Rakefile
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

112 lines
3.0 KiB
Ruby

require 'rake/clean'
require "bundler/gem_tasks"
require "rake/testtask"
require_relative "extsources"
SOURCES_DIR = "ext/sources"
SOURCES = FileList[]
EXTSOURCES.each do |src|
basename = src.pathmap("%f")
dest = basename == "LICENSE" ? basename
: src.pathmap("%{\\.\\./\\.\\.,#{SOURCES_DIR}}p")
.pathmap("%{\\.\\./javascript,#{SOURCES_DIR}/bindings/javascript}p")
dir = dest.pathmap("%d")
file src
directory dir
file dest => [src, dir] do |t|
copy t.source, t.name
end
SOURCES.include dest
end
CLEAN.include SOURCES
SRC = FileList["ext/*.{c,cpp,h}"]
task build: SOURCES
directory "pkg"
CLOBBER.include "pkg"
LIB_NAME = "whisper".ext(RbConfig::CONFIG["DLEXT"])
SO_FILE = File.join("ext", LIB_NAME)
LIB_FILE = File.join("lib", LIB_NAME)
file "ext/Makefile" => SRC + SOURCES + FileList["ext/*.rb"] do |t|
chdir "ext" do
ruby "extconf.rb"
end
end
if File.exist? "ext/Makefile"
task :make_clean do
cd "ext" do
sh "make", "clean"
end
end
task clean: :make_clean
task :make_distclean do
cd "ext" do
sh "make", "distclean"
end
end
task clobber: :make_distclean
end
file SO_FILE => "ext/Makefile" do |t|
chdir "ext" do
sh "make"
end
end
CLEAN.include SO_FILE
directory "lib"
file LIB_FILE => [SO_FILE, "lib"] do |t|
copy t.source, t.name
end
CLEAN.include LIB_FILE
Rake::TestTask.new
TEST_FIXTURE_AUDIO = "test/fixtures/jfk.wav"
TEST_FIXTURE_AUDIO_SRC = File.expand_path(File.join(__dir__, "..", "..", "samples", "jfk.wav"))
TEST_FIXTURE_AUDIO_DIR = TEST_FIXTURE_AUDIO.pathmap("%d")
directory TEST_FIXTURE_AUDIO_DIR
if File.exist? TEST_FIXTURE_AUDIO_SRC
file TEST_FIXTURE_AUDIO => [TEST_FIXTURE_AUDIO_SRC, TEST_FIXTURE_AUDIO_DIR] do |t|
symlink t.source, t.name
end
else
require "open-uri"
file TEST_FIXTURE_AUDIO => TEST_FIXTURE_AUDIO_DIR do |t|
File.write t.name, URI("https://github.com/ggml-org/whisper.cpp/raw/refs/heads/master/samples/jfk.wav").read
end
end
TEST_PARAKEET_MODEL = "test/fixtures/for-tests-ggml-parakeet-tdt.bin"
TEST_PARAKEET_MODEL_SRC = File.expand_path(File.join(__dir__, "..", "..", "models", "for-tests-ggml-parakeet-tdt.bin"))
TEST_PARAKEET_MODEL_DIR = TEST_PARAKEET_MODEL.pathmap("%d")
directory TEST_PARAKEET_MODEL_DIR
if File.exist? TEST_PARAKEET_MODEL_SRC
file TEST_PARAKEET_MODEL => [TEST_PARAKEET_MODEL_SRC, TEST_PARAKEET_MODEL_DIR] do |t|
symlink t.source, t.name
end
else
require "open-uri"
file TEST_PARAKEET_MODEL => TEST_PARAKEET_MODEL_DIR do |t|
File.write t.name, URI("https://github.com/ggml-org/whisper.cpp/raw/refs/heads/master/models/for-tests-ggml-parakeet-tdt.bin").read
end
end
TEST_MEMORY_VIEW = "test/jfk_reader/jfk_reader.#{RbConfig::CONFIG['DLEXT']}"
file TEST_MEMORY_VIEW => "test/jfk_reader/jfk_reader.c" do |t|
chdir "test/jfk_reader" do
ruby "extconf.rb"
sh "make"
end
end
CLEAN.include TEST_MEMORY_VIEW
task test: [LIB_FILE, TEST_MEMORY_VIEW, TEST_FIXTURE_AUDIO, TEST_PARAKEET_MODEL]