mirror of
https://github.com/ggml-org/whisper.cpp.git
synced 2026-07-23 11:10:57 -05:00
* 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
117 lines
3.3 KiB
Ruby
117 lines
3.3 KiB
Ruby
require_relative "helper"
|
|
require "stringio"
|
|
|
|
class TestParakeetContext < TestBase
|
|
def setup
|
|
omit "Skip not to download large model" if ENV["CI"]
|
|
|
|
Whisper.instance_variable_set "@whisper", nil
|
|
GC.start
|
|
|
|
@parakeet = Parakeet::Context.new("parakeet-tdt-0.6b-v3-q4_0")
|
|
@params = Parakeet::Params.new
|
|
end
|
|
|
|
def test_new
|
|
assert_instance_of Parakeet::Context, @parakeet
|
|
end
|
|
|
|
def test_new_with_params
|
|
log_callback = Parakeet.instance_variable_get(:@log_callback)
|
|
user_data = Parakeet.instance_variable_get(:@log_callback_user_data)
|
|
begin
|
|
logs = ""
|
|
Parakeet.log_set proc {|level, message| logs << message}, nil
|
|
params = Parakeet::Context::Params.new(use_gpu: false)
|
|
parakeet = Parakeet::Context.new("parakeet-tdt-0.6b-v3-q4_0", params)
|
|
assert_instance_of Parakeet::Context, parakeet
|
|
assert_match /use gpu\s+=\s+0/, logs
|
|
ensure
|
|
Parakeet.log_set log_callback, user_data
|
|
end
|
|
end
|
|
|
|
sub_test_case "full" do
|
|
def setup
|
|
super
|
|
@samples = File.read(AUDIO, nil, 78).unpack("s<*").collect {|i| i.to_f / 2**15}
|
|
end
|
|
|
|
def test_full
|
|
@parakeet.full @params, @samples, @samples.length
|
|
|
|
segments = @parakeet.each_segment.to_a
|
|
assert_equal 1, segments.length
|
|
assert_match /ask not what your country can do for you, ask what you can do for your/, segments.first.text
|
|
end
|
|
|
|
def test_full_without_length
|
|
@parakeet.full(@params, @samples)
|
|
|
|
segments = @parakeet.each_segment.to_a
|
|
assert_equal 1, segments.length
|
|
assert_match /ask not what your country can do for you, ask what you can do for your/, @parakeet.each_segment.first.text
|
|
end
|
|
|
|
def test_full_enumerator
|
|
samples = @samples.each
|
|
@parakeet.full @params, samples, @samples.length
|
|
|
|
segments = @parakeet.each_segment.to_a
|
|
assert_equal 1, segments.length
|
|
assert_match /ask not what your country can do for you, ask what you can do for your/, @parakeet.each_segment.first.text
|
|
end
|
|
|
|
def test_full_enumerator_without_length
|
|
samples = @samples.each
|
|
assert_raise ArgumentError do
|
|
@parakeet.full @params, samples
|
|
end
|
|
end
|
|
|
|
def test_full_enumerator_with_too_large_length
|
|
samples = @samples.each.take(10).to_enum
|
|
assert_raise StopIteration do
|
|
@parakeet.full @params, samples, 11
|
|
end
|
|
end
|
|
|
|
def test_full_with_memory_view
|
|
samples = JFKReader.new(AUDIO)
|
|
@parakeet.full @params, samples
|
|
|
|
segments = @parakeet.each_segment.to_a
|
|
assert_equal 1, segments.length
|
|
assert_match /ask not what your country can do for you, ask what you can do for your/, @parakeet.each_segment.first.text
|
|
end
|
|
|
|
def test_full_with_memroy_view_gc
|
|
samples = JFKReader.new(AUDIO)
|
|
@parakeet.full(@params, samples)
|
|
GC.start
|
|
require "fiddle"
|
|
Fiddle::MemoryView.export samples do |view|
|
|
assert_equal 176000, view.to_s.unpack("#{view.format}*").length
|
|
end
|
|
end
|
|
end
|
|
|
|
def test_transcribe
|
|
assert_nothing_raised do
|
|
@parakeet.transcribe AUDIO, @params
|
|
end
|
|
end
|
|
|
|
def test_transcribe_with_pathname
|
|
assert_nothing_raised do
|
|
@parakeet.transcribe Pathname(AUDIO), @params
|
|
end
|
|
end
|
|
|
|
def test_transcribe_with_nothing
|
|
assert_raise_message(/open/) do
|
|
@parakeet.transcribe "nothing", @params
|
|
end
|
|
end
|
|
end
|