whispercpp 1.3.1 → 1.3.2

data/tests/test_params.rb

@@ -1,6 +1,42 @@
 require_relative "helper"
 
 class TestParams < TestBase
+  PARAM_NAMES = [
+    :language,
+    :translate,
+    :no_context,
+    :single_segment,
+    :print_special,
+    :print_progress,
+    :print_realtime,
+    :print_timestamps,
+    :suppress_blank,
+    :suppress_nst,
+    :token_timestamps,
+    :split_on_word,
+    :initial_prompt,
+    :diarize,
+    :offset,
+    :duration,
+    :max_text_tokens,
+    :temperature,
+    :max_initial_ts,
+    :length_penalty,
+    :temperature_inc,
+    :entropy_thold,
+    :logprob_thold,
+    :no_speech_thold,
+    :new_segment_callback,
+    :new_segment_callback_user_data,
+    :progress_callback,
+    :progress_callback_user_data,
+    :abort_callback,
+    :abort_callback_user_data,
+    :vad,
+    :vad_model_path,
+    :vad_params,
+  ]
+
   def setup
     @params  = Whisper::Params.new
   end
@@ -89,11 +125,11 @@ class TestParams < TestBase
     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
+  def test_suppress_nst
+    @params.suppress_nst = true
+    assert @params.suppress_nst
+    @params.suppress_nst = false
+    assert !@params.suppress_nst
   end
 
   def test_token_timestamps
@@ -129,7 +165,7 @@ class TestParams < TestBase
   end
 
   def test_length_penalty
-    assert_equal -1.0, @params.length_penalty
+    assert_equal(-1.0, @params.length_penalty)
     @params.length_penalty = 0.5
     assert_equal 0.5, @params.length_penalty
   end
@@ -147,9 +183,9 @@ class TestParams < TestBase
   end
 
   def test_logprob_thold
-    assert_in_delta -1.0, @params.logprob_thold
+    assert_in_delta(-1.0, @params.logprob_thold)
     @params.logprob_thold = -0.5
-    assert_in_delta -0.5, @params.logprob_thold
+    assert_in_delta(-0.5, @params.logprob_thold)
   end
 
   def test_no_speech_thold
@@ -157,4 +193,105 @@ class TestParams < TestBase
     @params.no_speech_thold = 0.2
     assert_in_delta 0.2, @params.no_speech_thold
   end
+
+  def test_vad
+    assert_false @params.vad
+    @params.vad = true
+    assert_true @params.vad
+  end
+
+  def test_vad_model_path
+    assert_nil @params.vad_model_path
+    @params.vad_model_path = "silero-v5.1.2"
+    assert_equal Whisper::Model.pre_converted_models["silero-v5.1.2"].to_path, @params.vad_model_path
+  end
+
+  def test_vad_model_path_with_nil
+    @params.vad_model_path = "silero-v5.1.2"
+    @params.vad_model_path = nil
+    assert_nil @params.vad_model_path
+  end
+
+  def test_vad_model_path_with_invalid
+    assert_raise TypeError do
+      @params.vad_model_path = Object.new
+    end
+  end
+
+  def test_vad_model_path_with_URI_string
+    @params.vad_model_path = "https://huggingface.co/ggml-org/whisper-vad/resolve/main/ggml-silero-v5.1.2.bin"
+    assert_equal @params.vad_model_path, Whisper::Model.pre_converted_models["silero-v5.1.2"].to_path
+  end
+
+  def test_vad_model_path_with_URI
+    @params.vad_model_path = URI("https://huggingface.co/ggml-org/whisper-vad/resolve/main/ggml-silero-v5.1.2.bin")
+    assert_equal @params.vad_model_path, Whisper::Model.pre_converted_models["silero-v5.1.2"].to_path
+  end
+
+  def test_vad_params
+    assert_kind_of Whisper::VAD::Params, @params.vad_params
+    default_params = @params.vad_params
+    assert_same default_params, @params.vad_params
+    assert_equal 0.5, default_params.threshold
+    new_params = Whisper::VAD::Params.new
+    @params.vad_params = new_params
+    assert_same new_params, @params.vad_params
+  end
+
+  def test_new_with_kw_args
+    params = Whisper::Params.new(language: "es")
+    assert_equal "es", params.language
+    assert_equal 1.0, params.max_initial_ts
+  end
+
+  def test_new_with_kw_args_non_existent
+    assert_raise ArgumentError do
+      Whisper::Params.new(non_existent: "value")
+    end
+  end
+
+  def test_new_with_kw_args_wrong_type
+    assert_raise TypeError do
+      Whisper::Params.new(language: 3)
+    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 = case [param, default_value]
+            in [*, true | false]
+              !default_value
+            in [*, Integer | Float]
+              default_value + 1
+            in [:language, *]
+              "es"
+            in [:initial_prompt, *]
+              "Initial prompt"
+            in [/_callback\Z/, *]
+              proc {}
+            in [/_user_data\Z/, *]
+              Object.new
+            in [:vad_model_path, *]
+              Whisper::Model.pre_converted_models["silero-v5.1.2"].to_path
+            in [:vad_params, *]
+              Whisper::VAD::Params.new
+            end
+    params = Whisper::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_segment.rb

@@ -1,17 +1,6 @@
 require_relative "helper"
 
 class TestSegment < TestBase
-  class << self
-    attr_reader :whisper
-
-    def startup
-      @whisper = Whisper::Context.new("base.en")
-      params = Whisper::Params.new
-      params.print_timestamps = false
-      @whisper.transcribe(TestBase::AUDIO, params)
-    end
-  end
-
   def test_iteration
     whisper.each_segment do |segment|
       assert_instance_of Whisper::Segment, segment
@@ -43,6 +32,14 @@ class TestSegment < TestBase
     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
@@ -52,13 +49,13 @@ class TestSegment < TestBase
       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
+        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
+    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
@@ -74,10 +71,4 @@ class TestSegment < TestBase
     end
     whisper.transcribe(AUDIO, params)
   end
-
-  private
-
-  def whisper
-    self.class.whisper
-  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

@@ -16,26 +16,11 @@ class TestWhisper < TestBase
     params.print_timestamps = false
 
     @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
+      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
-    class << self
-      attr_reader :whisper
-
-      def startup
-        @whisper = Whisper::Context.new("base.en")
-        params = Whisper::Params.new
-        params.print_timestamps = false
-        @whisper.transcribe(TestBase::AUDIO, params)
-      end
-    end
-
-    def whisper
-      self.class.whisper
-    end
-
     def test_full_n_segments
       assert_equal 1, whisper.full_n_segments
     end
@@ -44,6 +29,12 @@ class TestWhisper < TestBase
       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
@@ -68,7 +59,13 @@ class TestWhisper < TestBase
     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)
+      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
 
@@ -137,14 +134,14 @@ class TestWhisper < TestBase
       @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
+      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
+      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
@@ -152,7 +149,7 @@ class TestWhisper < TestBase
       @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
+      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
@@ -174,26 +171,28 @@ class TestWhisper < TestBase
       @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
+      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
-      @whisper.full_parallel(@params, @samples, @samples.length, Etc.nprocessors)
+      nprocessors = 2
+      @whisper.full_parallel(@params, @samples, @samples.length, nprocessors)
 
-      assert_equal Etc.nprocessors, @whisper.full_n_segments
+      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
+      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, Etc.nprocessors)
+      @whisper.full_parallel(@params, samples, nil, nprocessors)
 
-      assert_equal Etc.nprocessors, @whisper.full_n_segments
+      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
+      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
@@ -201,17 +200,18 @@ class TestWhisper < TestBase
 
       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
+      assert_match(/ask what you can do/i, text)
+      assert_match(/for your country/i, text)
     end
 
     def test_full_parallel_without_length
-      @whisper.full_parallel(@params, @samples, nil, Etc.nprocessors)
+      nprocessors = 2
+      @whisper.full_parallel(@params, @samples, nil, nprocessors)
 
-      assert_equal Etc.nprocessors, @whisper.full_n_segments
+      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
+      assert_match(/ask what you can do/i, text)
+      assert_match(/for your country/i, text)
     end
 
     def test_full_parallel_without_n_processors
@@ -219,8 +219,8 @@ class TestWhisper < TestBase
 
       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
+      assert_match(/ask what you can do/i, text)
+      assert_match(/for your country/i, text)
     end
   end
 end

data/whispercpp.gemspec

@@ -3,8 +3,8 @@ require_relative "extsources"
 Gem::Specification.new do |s|
   s.name    = "whispercpp"
   s.authors = ["Georgi Gerganov", "Todd A. Fisher"]
-  s.version = '1.3.1'
-  s.date    = '2024-12-19'
+  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']
@@ -15,7 +15,8 @@ Gem::Specification.new do |s|
                 if s.extra_rdoc_files.include?(basename)
                   basename
                 else
-                  file.sub("../..", "ext")
+                  file.sub("../..", "ext/sources")
+                      .sub("../javascript", "ext/sources/bindings/javascript")
                 end
               }
 
@@ -26,7 +27,7 @@ Gem::Specification.new do |s|
   s.required_ruby_version = '>= 3.1.0'
 
   #### Documentation and testing.
-  s.homepage = 'https://github.com/ggerganov/whisper.cpp'
+  s.homepage = 'https://github.com/ggml-org/whisper.cpp'
   s.rdoc_options = ['--main', 'README.md']