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
204 lines
5.3 KiB
Ruby
204 lines
5.3 KiB
Ruby
require_relative "helper"
|
|
|
|
class TestCallback < TestBase
|
|
def setup
|
|
GC.start
|
|
@params = Whisper::Params.new
|
|
@whisper = Whisper::Context.new("base.en")
|
|
@audio = File.join(AUDIO)
|
|
end
|
|
|
|
def test_new_segment_callback
|
|
@params.new_segment_callback = ->(context, state, n_new, user_data) {
|
|
assert_kind_of Integer, n_new
|
|
assert n_new > 0
|
|
assert_same @whisper, context
|
|
|
|
n_segments = context.full_n_segments
|
|
n_new.times do |i|
|
|
i_segment = n_segments - 1 + i
|
|
start_time = context.full_get_segment_t0(i_segment) * 10
|
|
end_time = context.full_get_segment_t1(i_segment) * 10
|
|
text = context.full_get_segment_text(i_segment)
|
|
|
|
assert_kind_of Integer, start_time
|
|
assert start_time >= 0
|
|
assert_kind_of Integer, end_time
|
|
assert end_time > 0
|
|
assert_match(/ask not what your country can do for you, ask what you can do for your country/, text) if i_segment == 0
|
|
end
|
|
}
|
|
|
|
@whisper.transcribe(@audio, @params)
|
|
end
|
|
|
|
def test_new_segment_callback_closure
|
|
search_word = "what"
|
|
@params.new_segment_callback = ->(context, state, n_new, user_data) {
|
|
n_segments = context.full_n_segments
|
|
n_new.times do |i|
|
|
i_segment = n_segments - 1 + i
|
|
text = context.full_get_segment_text(i_segment)
|
|
if text.include?(search_word)
|
|
t0 = context.full_get_segment_t0(i_segment)
|
|
t1 = context.full_get_segment_t1(i_segment)
|
|
raise "search word '#{search_word}' found at between #{t0} and #{t1}"
|
|
end
|
|
end
|
|
}
|
|
|
|
assert_raise RuntimeError do
|
|
@whisper.transcribe(@audio, @params)
|
|
end
|
|
end
|
|
|
|
def test_new_segment_callback_user_data
|
|
udata = Object.new
|
|
@params.new_segment_callback_user_data = udata
|
|
@params.new_segment_callback = ->(context, state, n_new, user_data) {
|
|
assert_same udata, user_data
|
|
}
|
|
|
|
@whisper.transcribe(@audio, @params)
|
|
end
|
|
|
|
def test_new_segment_callback_user_data_gc
|
|
@params.new_segment_callback_user_data = "My user data"
|
|
@params.new_segment_callback = ->(context, state, n_new, user_data) {
|
|
assert_equal "My user data", user_data
|
|
}
|
|
GC.start
|
|
|
|
assert_same @whisper, @whisper.transcribe(@audio, @params)
|
|
end
|
|
|
|
def test_progress_callback
|
|
first = nil
|
|
last = nil
|
|
@params.progress_callback = ->(context, state, progress, user_data) {
|
|
assert_kind_of Integer, progress
|
|
assert 0 <= progress && progress <= 100
|
|
assert_same @whisper, context
|
|
first = progress if first.nil?
|
|
last = progress
|
|
}
|
|
@whisper.transcribe(@audio, @params)
|
|
assert_equal 0, first
|
|
assert_equal 100, last
|
|
end
|
|
|
|
def test_progress_callback_user_data
|
|
udata = Object.new
|
|
@params.progress_callback_user_data = udata
|
|
@params.progress_callback = ->(context, state, n_new, user_data) {
|
|
assert_same udata, user_data
|
|
}
|
|
|
|
@whisper.transcribe(@audio, @params)
|
|
end
|
|
|
|
def test_on_progress
|
|
first = nil
|
|
last = nil
|
|
@params.on_progress do |progress|
|
|
assert_kind_of Integer, progress
|
|
assert 0 <= progress && progress <= 100
|
|
first = progress if first.nil?
|
|
last = progress
|
|
end
|
|
@whisper.transcribe(@audio, @params)
|
|
assert_equal 0, first
|
|
assert_equal 100, last
|
|
end
|
|
|
|
def test_encoder_begin_callback
|
|
i = 0
|
|
@params.encoder_begin_callback = ->(context, state, user_data) {
|
|
i += 1
|
|
}
|
|
@whisper.transcribe(@audio, @params)
|
|
assert i > 0
|
|
end
|
|
|
|
def test_encoder_begin_callback_abort
|
|
logs = []
|
|
Whisper.log_set -> (level, buffer, user_data) {
|
|
logs << buffer if level == Whisper::LOG_LEVEL_ERROR
|
|
}, logs
|
|
@params.encoder_begin_callback = ->(context, state, user_data) {
|
|
return false
|
|
}
|
|
@whisper.transcribe(@audio, @params)
|
|
sleep 0.5 # wait for logs dequeued
|
|
assert_match(/encoder_begin_callback returned false - aborting/, logs.join)
|
|
Whisper.log_set ->(level, buffer, user_data) {}, nil
|
|
end
|
|
|
|
def test_encoder_begin_callback_user_data
|
|
udata = Object.new
|
|
@params.encoder_begin_callback_user_data = udata
|
|
yielded = nil
|
|
@params.encoder_begin_callback = ->(context, state, user_data) {
|
|
yielded = user_data
|
|
}
|
|
@whisper.transcribe(@audio, @params)
|
|
assert_same udata, yielded
|
|
end
|
|
|
|
def test_on_encoder_begin
|
|
i = 0
|
|
@params.on_encoder_begin do
|
|
i += 1
|
|
end
|
|
@whisper.transcribe(@audio, @params)
|
|
assert i > 0
|
|
end
|
|
|
|
def test_abort_callback
|
|
i = 0
|
|
@params.abort_callback = ->(user_data) {
|
|
assert_nil user_data
|
|
i += 1
|
|
return false
|
|
}
|
|
@whisper.transcribe(@audio, @params)
|
|
assert i > 0
|
|
end
|
|
|
|
def test_abort_callback_abort
|
|
i = 0
|
|
@params.abort_callback = ->(user_data) {
|
|
i += 1
|
|
return i == 3
|
|
}
|
|
@whisper.transcribe(@audio, @params)
|
|
assert_equal 3, i
|
|
end
|
|
|
|
def test_abort_callback_user_data
|
|
udata = Object.new
|
|
@params.abort_callback_user_data = udata
|
|
yielded = nil
|
|
@params.abort_callback = ->(user_data) {
|
|
yielded = user_data
|
|
}
|
|
@whisper.transcribe(@audio, @params)
|
|
assert_same udata, yielded
|
|
end
|
|
|
|
def test_abort_on
|
|
do_abort = false
|
|
_aborted_from_callback = false
|
|
@params.on_new_segment do |segment|
|
|
do_abort = true if segment.text.match?(/ask/)
|
|
end
|
|
i = 0
|
|
@params.abort_on do
|
|
i += 1
|
|
do_abort
|
|
end
|
|
@whisper.transcribe(@audio, @params)
|
|
assert i > 0
|
|
end
|
|
end
|