whispercpp 1.3.0 → 1.3.2

data/tests/test_segment.rb

@@ -0,0 +1,74 @@
+require_relative "helper"
+
+class TestSegment < TestBase
+  def test_iteration
+    whisper.each_segment do |segment|
+      assert_instance_of Whisper::Segment, segment
+    end
+  end
+
+  def test_enumerator
+    enum = whisper.each_segment
+    assert_instance_of Enumerator, enum
+    enum.to_a.each_with_index do |segment, index|
+      assert_instance_of Whisper::Segment, segment
+      assert_kind_of Integer, index
+    end
+  end
+
+  def test_start_time
+    i = 0
+    whisper.each_segment do |segment|
+      assert_equal 0, segment.start_time if i == 0
+      i += 1
+    end
+  end
+
+  def test_end_time
+    i = 0
+    whisper.each_segment do |segment|
+      assert_equal whisper.full_get_segment_t1(i) * 10, segment.end_time
+      i += 1
+    end
+  end
+
+  def test_no_speech_prob
+    no_speech_prob = nil
+    whisper.each_segment do |segment|
+      no_speech_prob = segment.no_speech_prob
+    end
+    assert no_speech_prob > 0.0
+  end
+
+  def test_on_new_segment
+    params = Whisper::Params.new
+    seg = nil
+    index = 0
+    params.on_new_segment do |segment|
+      assert_instance_of Whisper::Segment, segment
+      if index == 0
+        seg = segment
+        assert_equal 0, segment.start_time
+        assert_match(/ask not what your country can do for you, ask what you can do for your country/, segment.text)
+      end
+      index += 1
+    end
+    whisper.transcribe(AUDIO, params)
+    assert_equal 0, seg.start_time
+    assert_match(/ask not what your country can do for you, ask what you can do for your country/, seg.text)
+  end
+
+  def test_on_new_segment_twice
+    params = Whisper::Params.new
+    seg = nil
+    params.on_new_segment do |segment|
+      seg = segment
+      return
+    end
+    params.on_new_segment do |segment|
+      assert_same seg, segment
+      return
+    end
+    whisper.transcribe(AUDIO, params)
+  end
+end

data/tests/test_vad.rb

@@ -0,0 +1,19 @@
+require_relative "helper"
+
+class TestVAD < TestBase
+  def setup
+    @whisper = Whisper::Context.new("base.en")
+    vad_params = Whisper::VAD::Params.new
+    @params = Whisper::Params.new(
+      vad: true,
+      vad_model_path: "silero-v5.1.2",
+      vad_params:
+    )
+  end
+
+  def test_transcribe
+    @whisper.transcribe(TestBase::AUDIO, @params) do |text|
+      assert_match(/ask not what your country can do for you[,.] ask what you can do for your country/i, text)
+    end
+  end
+end

data/tests/test_vad_params.rb

@@ -0,0 +1,103 @@
+require_relative "helper"
+
+class TestVADParams < TestBase
+  PARAM_NAMES = [
+    :threshold,
+    :min_speech_duration_ms,
+    :min_silence_duration_ms,
+    :max_speech_duration_s,
+    :speech_pad_ms,
+    :samples_overlap
+  ]
+
+  def setup
+    @params = Whisper::VAD::Params.new
+  end
+
+  def test_new
+    params = Whisper::VAD::Params.new
+    assert_kind_of Whisper::VAD::Params, params
+  end
+
+  def test_threshold
+    assert_in_delta @params.threshold, 0.5
+    @params.threshold = 0.7
+    assert_in_delta @params.threshold, 0.7
+  end
+
+  def test_min_speech_duration
+    pend
+  end
+
+  def test_min_speech_duration_ms
+    assert_equal 250, @params.min_speech_duration_ms
+    @params.min_speech_duration_ms = 500
+    assert_equal 500, @params.min_speech_duration_ms
+  end
+
+  def test_min_silence_duration_ms
+    assert_equal 100, @params.min_silence_duration_ms
+    @params.min_silence_duration_ms = 200
+    assert_equal 200, @params.min_silence_duration_ms
+  end
+
+  def test_max_speech_duration
+    pend
+  end
+
+  def test_max_speech_duration_s
+    assert @params.max_speech_duration_s >= 10e37 # Defaults to FLT_MAX
+    @params.max_speech_duration_s = 60.0
+    assert_equal 60.0, @params.max_speech_duration_s
+  end
+
+  def test_speech_pad_ms
+    assert_equal 30, @params.speech_pad_ms
+    @params.speech_pad_ms = 50
+    assert_equal 50, @params.speech_pad_ms
+  end
+
+  def test_samples_overlap
+    assert_in_delta @params.samples_overlap, 0.1
+    @params.samples_overlap = 0.5
+    assert_in_delta @params.samples_overlap, 0.5
+  end
+
+  def test_equal
+    assert_equal @params, Whisper::VAD::Params.new
+  end
+
+  def test_new_with_kw_args
+    params = Whisper::VAD::Params.new(threshold: 0.7)
+    assert_in_delta params.threshold, 0.7
+    assert_equal 250, params.min_speech_duration_ms
+  end
+
+  def test_new_with_kw_args_non_existent
+    assert_raise ArgumentError do
+      Whisper::VAD::Params.new(non_existent: "value")
+    end
+  end
+
+  data(PARAM_NAMES.collect {|param| [param, param]}.to_h)
+  def test_new_with_kw_args_default_values(param)
+    default_value = @params.send(param)
+    value = default_value + 1
+    params = Whisper::VAD::Params.new(param => value)
+    if Float === value
+      assert_in_delta value, params.send(param)
+    else
+      assert_equal value, params.send(param)
+    end
+
+    PARAM_NAMES.reject {|name| name == param}.each do |name|
+      expected = @params.send(name)
+      actual = params.send(name)
+      if Float === expected
+        assert_in_delta expected, actual
+      else
+        assert_equal expected, actual
+      end
+    end
+  end
+end

data/tests/test_whisper.rb

@@ -1,138 +1,226 @@
-TOPDIR = File.expand_path(File.join(File.dirname(__FILE__), '..'))
-EXTDIR = File.join(TOPDIR, 'ext')
-#$LIBDIR = File.join(TOPDIR, 'lib')
-#$:.unshift(LIBDIR)
-$:.unshift(EXTDIR)
+require_relative "helper"
+require "stringio"
+require "etc"
 
-require 'whisper'
-require 'test/unit'
+# Exists to detect memory-related bug
+Whisper.log_set ->(level, buffer, user_data) {}, nil
 
-class TestWhisper < Test::Unit::TestCase
+class TestWhisper < TestBase
   def setup
     @params  = Whisper::Params.new
   end
 
-  def test_language
-    @params.language = "en"
-    assert_equal @params.language, "en"
-    @params.language = "auto"
-    assert_equal @params.language, "auto"
-  end
-
-  def test_offset
-    @params.offset = 10_000
-    assert_equal @params.offset, 10_000
-    @params.offset = 0
-    assert_equal @params.offset, 0
-  end
-
-  def test_duration
-    @params.duration = 60_000
-    assert_equal @params.duration, 60_000
-    @params.duration = 0
-    assert_equal @params.duration, 0
-  end
-
-  def test_max_text_tokens
-    @params.max_text_tokens = 300
-    assert_equal @params.max_text_tokens, 300
-    @params.max_text_tokens = 0
-    assert_equal @params.max_text_tokens, 0
-  end
-
-  def test_translate
-    @params.translate = true
-    assert @params.translate
-    @params.translate = false
-    assert !@params.translate
-  end
-
-  def test_no_context
-    @params.no_context = true
-    assert @params.no_context
-    @params.no_context = false
-    assert !@params.no_context
-  end
-
-  def test_single_segment
-    @params.single_segment = true
-    assert @params.single_segment
-    @params.single_segment = false
-    assert !@params.single_segment
-  end
-
-  def test_print_special
-    @params.print_special = true
-    assert @params.print_special
-    @params.print_special = false
-    assert !@params.print_special
-  end
-
-  def test_print_progress
-    @params.print_progress = true
-    assert @params.print_progress
-    @params.print_progress = false
-    assert !@params.print_progress
-  end
-
-  def test_print_realtime
-    @params.print_realtime = true
-    assert @params.print_realtime
-    @params.print_realtime = false
-    assert !@params.print_realtime
-  end
-
-  def test_print_timestamps
-    @params.print_timestamps = true
-    assert @params.print_timestamps
-    @params.print_timestamps = false
-    assert !@params.print_timestamps
-  end
-
-  def test_suppress_blank
-    @params.suppress_blank = true
-    assert @params.suppress_blank
-    @params.suppress_blank = false
-    assert !@params.suppress_blank
-  end
-
-  def test_suppress_non_speech_tokens
-    @params.suppress_non_speech_tokens = true
-    assert @params.suppress_non_speech_tokens
-    @params.suppress_non_speech_tokens = false
-    assert !@params.suppress_non_speech_tokens
-  end
-
-  def test_token_timestamps
-    @params.token_timestamps = true
-    assert @params.token_timestamps
-    @params.token_timestamps = false
-    assert !@params.token_timestamps
-  end
-
-  def test_split_on_word
-    @params.split_on_word = true
-    assert @params.split_on_word
-    @params.split_on_word = false
-    assert !@params.split_on_word
-  end
-
-  def test_speed_up
-    @params.speed_up = true
-    assert @params.speed_up
-    @params.speed_up = false
-    assert !@params.speed_up
-  end
-
   def test_whisper
-    @whisper = Whisper::Context.new(File.join(TOPDIR, '..', '..', 'models', 'ggml-base.en.bin'))
+    @whisper = Whisper::Context.new("base.en")
     params  = Whisper::Params.new
     params.print_timestamps = false
 
-    jfk = File.join(TOPDIR, '..', '..', 'samples', 'jfk.wav')
-    @whisper.transcribe(jfk, params) {|text|
-      assert_match /ask not what your country can do for you, ask what you can do for your country/, text
+    @whisper.transcribe(AUDIO, params) {|text|
+      assert_match(/ask not what your country can do for you, ask what you can do for your country/, text)
     }
   end
 
+  sub_test_case "After transcription" do
+    def test_full_n_segments
+      assert_equal 1, whisper.full_n_segments
+    end
+
+    def test_full_lang_id
+      assert_equal 0, whisper.full_lang_id
+    end
+
+    def test_full_get_segment
+      segment = whisper.full_get_segment(0)
+      assert_equal 0, segment.start_time
+      assert_match(/ask not what your country can do for you, ask what you can do for your country/, segment.text)
+    end
+
+    def test_full_get_segment_t0
+      assert_equal 0, whisper.full_get_segment_t0(0)
+      assert_raise IndexError do
+        whisper.full_get_segment_t0(whisper.full_n_segments)
+      end
+      assert_raise IndexError do
+        whisper.full_get_segment_t0(-1)
+      end
+    end
+
+    def test_full_get_segment_t1
+      t1 = whisper.full_get_segment_t1(0)
+      assert_kind_of Integer, t1
+      assert t1 > 0
+      assert_raise IndexError do
+        whisper.full_get_segment_t1(whisper.full_n_segments)
+      end
+    end
+
+    def test_full_get_segment_speaker_turn_next
+      assert_false whisper.full_get_segment_speaker_turn_next(0)
+    end
+
+    def test_full_get_segment_text
+      assert_match(/ask not what your country can do for you, ask what you can do for your country/, whisper.full_get_segment_text(0))
+    end
+
+    def test_full_get_segment_no_speech_prob
+      prob = whisper.full_get_segment_no_speech_prob(0)
+      assert prob > 0.0
+      assert prob < 1.0
+    end
+  end
+
+  def test_lang_max_id
+    assert_kind_of Integer, Whisper.lang_max_id
+  end
+
+  def test_lang_id
+    assert_equal 0, Whisper.lang_id("en")
+    assert_raise ArgumentError do
+      Whisper.lang_id("non existing language")
+    end
+  end
+
+  def test_lang_str
+    assert_equal "en", Whisper.lang_str(0)
+    assert_raise IndexError do
+      Whisper.lang_str(Whisper.lang_max_id + 1)
+    end
+  end
+
+  def test_lang_str_full
+    assert_equal "english", Whisper.lang_str_full(0)
+    assert_raise IndexError do
+      Whisper.lang_str_full(Whisper.lang_max_id + 1)
+    end
+  end
+
+  def test_log_set
+    user_data = Object.new
+    logs = []
+    log_callback = ->(level, buffer, udata) {
+      logs << [level, buffer, udata]
+    }
+    Whisper.log_set log_callback, user_data
+    Whisper::Context.new("base.en")
+
+    assert logs.length > 30
+    logs.each do |log|
+      assert_include [Whisper::LOG_LEVEL_DEBUG, Whisper::LOG_LEVEL_INFO, Whisper::LOG_LEVEL_WARN], log[0]
+      assert_same user_data, log[2]
+    end
+  end
+
+  def test_log_suppress
+    stderr = $stderr
+    Whisper.log_set ->(level, buffer, user_data) {
+      # do nothing
+    }, nil
+    dev = StringIO.new("")
+    $stderr = dev
+    Whisper::Context.new("base.en")
+    assert_empty dev.string
+  ensure
+    $stderr = stderr
+  end
+
+  sub_test_case "full" do
+    def setup
+      super
+      @whisper = Whisper::Context.new("base.en")
+      @samples = File.read(AUDIO, nil, 78).unpack("s<*").collect {|i| i.to_f / 2**15}
+    end
+
+    def test_full
+      @whisper.full(@params, @samples, @samples.length)
+
+      assert_equal 1, @whisper.full_n_segments
+      assert_match(/ask not what your country can do for you, ask what you can do for your country/, @whisper.each_segment.first.text)
+    end
+
+    def test_full_without_length
+      @whisper.full(@params, @samples)
+
+      assert_equal 1, @whisper.full_n_segments
+      assert_match(/ask not what your country can do for you, ask what you can do for your country/, @whisper.each_segment.first.text)
+    end
+
+    def test_full_enumerator
+      samples = @samples.each
+      @whisper.full(@params, samples, @samples.length)
+
+      assert_equal 1, @whisper.full_n_segments
+      assert_match(/ask not what your country can do for you, ask what you can do for your country/, @whisper.each_segment.first.text)
+    end
+
+    def test_full_enumerator_without_length
+      samples = @samples.each
+      assert_raise ArgumentError do
+        @whisper.full(@params, samples)
+      end
+    end
+
+    def test_full_enumerator_with_too_large_length
+      samples = @samples.each.take(10).to_enum
+      assert_raise StopIteration do
+        @whisper.full(@params, samples, 11)
+      end
+    end
+
+    def test_full_with_memory_view
+      samples = JFKReader.new(AUDIO)
+      @whisper.full(@params, samples)
+
+      assert_equal 1, @whisper.full_n_segments
+      assert_match(/ask not what your country can do for you, ask what you can do for your country/, @whisper.each_segment.first.text)
+    end
+
+    def test_full_parallel
+      nprocessors = 2
+      @whisper.full_parallel(@params, @samples, @samples.length, nprocessors)
+
+      assert_equal nprocessors, @whisper.full_n_segments
+      text = @whisper.each_segment.collect(&:text).join
+      assert_match(/ask what you can do/i, text)
+      assert_match(/for your country/i, text)
+    end
+
+    def test_full_parallel_with_memory_view
+      nprocessors = 2
+      samples = JFKReader.new(AUDIO)
+      @whisper.full_parallel(@params, samples, nil, nprocessors)
+
+      assert_equal nprocessors, @whisper.full_n_segments
+      text = @whisper.each_segment.collect(&:text).join
+      assert_match(/ask what you can do/i, text)
+      assert_match(/for your country/i, text)
+    end
+
+    def test_full_parallel_without_length_and_n_processors
+      @whisper.full_parallel(@params, @samples)
+
+      assert_equal 1, @whisper.full_n_segments
+      text = @whisper.each_segment.collect(&:text).join
+      assert_match(/ask what you can do/i, text)
+      assert_match(/for your country/i, text)
+    end
+
+    def test_full_parallel_without_length
+      nprocessors = 2
+      @whisper.full_parallel(@params, @samples, nil, nprocessors)
+
+      assert_equal nprocessors, @whisper.full_n_segments
+      text = @whisper.each_segment.collect(&:text).join
+      assert_match(/ask what you can do/i, text)
+      assert_match(/for your country/i, text)
+    end
+
+    def test_full_parallel_without_n_processors
+      @whisper.full_parallel(@params, @samples, @samples.length)
+
+      assert_equal 1, @whisper.full_n_segments
+      text = @whisper.each_segment.collect(&:text).join
+      assert_match(/ask what you can do/i, text)
+      assert_match(/for your country/i, text)
+    end
+  end
 end

data/whispercpp.gemspec

@@ -0,0 +1,37 @@
+require_relative "extsources"
+
+Gem::Specification.new do |s|
+  s.name    = "whispercpp"
+  s.authors = ["Georgi Gerganov", "Todd A. Fisher"]
+  s.version = '1.3.2'
+  s.date    = '2025-05-11'
+  s.description = %q{High-performance inference of OpenAI's Whisper automatic speech recognition (ASR) model via Ruby}
+  s.email   = 'todd.fisher@gmail.com'
+  s.extra_rdoc_files = ['LICENSE', 'README.md']
+
+  s.files = `git ls-files . -z`.split("\x0") +
+              EXTSOURCES.collect {|file|
+                basename = File.basename(file)
+                if s.extra_rdoc_files.include?(basename)
+                  basename
+                else
+                  file.sub("../..", "ext/sources")
+                      .sub("../javascript", "ext/sources/bindings/javascript")
+                end
+              }
+
+  s.summary = %q{Ruby whisper.cpp bindings}
+  s.test_files = s.files.select {|file| file.start_with? "tests/"}
+
+  s.extensions << 'ext/extconf.rb'
+  s.required_ruby_version = '>= 3.1.0'
+
+  #### Documentation and testing.
+  s.homepage = 'https://github.com/ggml-org/whisper.cpp'
+  s.rdoc_options = ['--main', 'README.md']
+
+
+    s.platform = Gem::Platform::RUBY
+
+  s.licenses = ['MIT']
+end