whispercpp 1.3.6 → 1.3.8

data/test/jfk_reader/jfk_reader.c

@@ -2,6 +2,24 @@
 #include <ruby/memory_view.h>
 #include <ruby/encoding.h>
 
+typedef struct {
+    VALUE audio_path;
+    int   n_samples;
+    const char *audio_path_str;
+    float      *data;
+    short      *samples;
+} jfk_alloc_args;
+
+static VALUE
+jfk_reader_alloc_resources(VALUE arg)
+{
+    jfk_alloc_args *a = (jfk_alloc_args *)arg;
+    a->audio_path_str = StringValueCStr(a->audio_path);
+    a->data    = ALLOC_N(float, a->n_samples);
+    a->samples = ALLOC_N(short, a->n_samples);
+    return Qnil;
+}
+
 static VALUE
 jfk_reader_initialize(VALUE self, VALUE audio_path)
 {
@@ -13,21 +31,42 @@ static bool
 jfk_reader_get_memory_view(const VALUE obj, rb_memory_view_t *view, int flags)
 {
   VALUE audio_path = rb_iv_get(obj, "audio_path");
-  const char *audio_path_str = StringValueCStr(audio_path);
+  // n_samples is a fixed constant (not derived from user input).
   const int n_samples = 176000;
-  float *data = (float *)malloc(n_samples * sizeof(float));
-  short *samples = (short *)malloc(n_samples * sizeof(short));
-  FILE *file = fopen(audio_path_str, "rb");
+
+  jfk_alloc_args args = {
+    .audio_path = audio_path,
+    .n_samples  = n_samples,
+    .audio_path_str = NULL,
+    .data    = NULL,
+    .samples = NULL,
+  };
+
+  int state;
+  rb_protect(jfk_reader_alloc_resources, (VALUE)&args, &state);
+  if (state) {
+    if (args.samples) xfree(args.samples);
+    if (args.data)    xfree(args.data);
+    return false;
+  }
+
+  FILE *file = fopen(args.audio_path_str, "rb");
+  if (file == NULL) {
+    xfree(args.samples);
+    xfree(args.data);
+    return false;
+  }
 
   fseek(file, 78, SEEK_SET);
-  fread(samples, sizeof(short), n_samples, file);
+  fread(args.samples, sizeof(short), n_samples, file);
   fclose(file);
   for (int i = 0; i < n_samples; i++) {
-    data[i] = samples[i]/32768.0;
+    args.data[i] = args.samples[i] / 32768.0;
   }
+  xfree(args.samples);
 
   view->obj = obj;
-  view->data = (void *)data;
+  view->data = (void *)args.data;
   view->byte_size = sizeof(float) * n_samples;
   view->readonly = true;
   view->format = "f";
@@ -45,6 +84,10 @@ jfk_reader_get_memory_view(const VALUE obj, rb_memory_view_t *view, int flags)
 static bool
 jfk_reader_release_memory_view(const VALUE obj, rb_memory_view_t *view)
 {
+  if (view->data) {
+    xfree(view->data);
+    view->data = NULL;
+  }
   return true;
 }
 

data/test/test_callback.rb

@@ -129,6 +129,7 @@ class TestCallback < TestBase
       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

data/test/test_package.rb

@@ -1,12 +1,12 @@
 require_relative "helper"
 require 'tempfile'
 require 'tmpdir'
-require 'shellwords'
+require 'open3'
 
 class TestPackage < TestBase
   def test_build
     Tempfile.create do |file|
-      assert system("gem", "build", "whispercpp.gemspec", "--output", file.to_path.shellescape, exception: true)
+      assert system("gem", "build", "whispercpp.gemspec", "--output", file.to_path, exception: true)
       assert file.size > 0
       assert_path_exist file.to_path
     end
@@ -20,7 +20,7 @@ class TestPackage < TestBase
     def test_install
       gemspec = Gem::Specification.load("whispercpp.gemspec")
       Dir.mktmpdir do |dir|
-        system "gem", "install", "--install-dir", dir.shellescape, "--no-document", "pkg/#{gemspec.file_name.shellescape}", exception: true
+        system "gem", "install", "--install-dir", dir, "--no-document", File.join("pkg", gemspec.file_name), exception: true
         assert_installed dir, gemspec.version
       end
     end
@@ -29,13 +29,14 @@ class TestPackage < TestBase
       omit_unless RUBY_PLATFORM.match?(/darwin/) do
         gemspec = Gem::Specification.load("whispercpp.gemspec")
         Dir.mktmpdir do |dir|
-          system "gem", "install", "--install-dir", dir.shellescape, "--no-document", "pkg/#{gemspec.file_name.shellescape}", "--", "--enable-whisper-coreml", exception: true
+          system "gem", "install", "--install-dir", dir, "--no-document", File.join("pkg", gemspec.file_name), "--", "--enable-whisper-coreml", exception: true
           assert_installed dir, gemspec.version
           libdir = File.join(dir, "gems", "#{gemspec.name}-#{gemspec.version}", "lib")
           assert_nothing_raised do
             system "ruby", "-I", libdir, "-r", "whisper", "-e", "Whisper::Context.new('tiny')", exception: true
           end
-          assert_match(/COREML = 1/, `ruby -I #{libdir.shellescape} -r whisper -e 'puts Whisper.system_info_str'`)
+          output, status = Open3.capture2("ruby", "-I", libdir, "-r", "whisper", "-e", "puts Whisper.system_info_str")
+          assert_match /COREML = 1/, output
         end
       end
     end

data/test/test_parakeet.rb

@@ -0,0 +1,28 @@
+require_relative "helper"
+require "stringio"
+
+class TestParakeet < TestBase
+  def test_log_set
+    log_callback = Parakeet.instance_variable_get("@log_callback")
+    user_data = Parakeet.instance_variable_get("@log_callback_user_data")
+
+    $stdout = StringIO.new
+    Parakeet.log_set proc {|level, message, _| puts [level, message].join(": ")}, nil
+    Parakeet::Context.new("test/fixtures/for-tests-ggml-parakeet-tdt.bin")
+    sleep 0.1
+    $stdout.rewind
+    logs = $stdout.string
+    assert_match /loading model from/, logs
+  ensure
+    $stdout = STDOUT
+    Parakeet.log_set log_callback, user_data
+  end
+
+  def test_system_info_str
+    assert_match /\APARAKEET : /, Parakeet.system_info_str
+  end
+
+  def test_version
+    assert_instance_of String, Parakeet::VERSION
+  end
+end

data/test/test_parakeet_callback.rb

@@ -0,0 +1,107 @@
+require_relative "helper"
+
+class TestParakeetCallback < TestBase
+  def setup
+    omit "Skip not to download large model" if ENV["CI"]
+
+    Whisper.instance_variable_set "@whisper", nil
+    GC.start
+    @params = Parakeet::Params.new
+    @parakeet = Parakeet::Context.new("parakeet-tdt-0.6b-v3-q4_0")
+  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 @parakeet, 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/, text) if i_segment == 0
+      end
+    }
+
+    @parakeet.transcribe AUDIO, @params
+  end
+
+  def test_on_new_segment
+    seg = nil
+    index = 0
+    @params.on_new_segment do |segment|
+      assert_instance_of Parakeet::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/, segment.text)
+      end
+      index += 1
+    end
+    @parakeet.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/, seg.text
+  end
+
+  def test_on_new_token
+    index = 0
+    @params.on_new_token do |token|
+      assert_instance_of Parakeet::Token, token
+      if index == 0
+        assert_instance_of Integer, token.start_time
+        assert_match "▁And", token.text
+      end
+      index += 1
+    end
+
+    @parakeet.transcribe AUDIO, @params
+  end
+
+  def test_on_progress
+    first = nil
+    @params.on_progress do |progress|
+      assert_kind_of Integer, progress
+      assert 0 <= progress && progress <= 100
+      first = progress if first.nil?
+    end
+
+    @parakeet.transcribe AUDIO, @params
+
+    assert_equal 0, first
+  end
+
+  def test_on_encoder_begin
+    i = 0
+    @params.on_encoder_begin do
+      i += 1
+    end
+
+    @parakeet.transcribe AUDIO, @params
+
+    assert i > 0
+  end
+
+  def test_abort_on
+    do_abort = 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
+
+    @parakeet.transcribe(AUDIO, @params) rescue nil
+
+    assert i > 0
+  end
+end

data/test/test_parakeet_context.rb

@@ -0,0 +1,116 @@
+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

data/test/test_parakeet_context_params.rb

@@ -0,0 +1,24 @@
+require_relative "helper"
+
+class TestParakeetContextParams < TestBase
+  def setup
+    @params = Parakeet::Context::Params.new
+  end
+
+  def test_new
+    assert_instance_of Parakeet::Context::Params, @params
+  end
+
+  def test_attributes
+    assert_true @params.use_gpu
+    assert_instance_of Integer, @params.gpu_device
+  end
+
+  def test_attribute_writer
+    @params.use_gpu = false
+    assert_false @params.use_gpu
+
+    @params.gpu_device = 2
+    assert_equal 2, @params.gpu_device
+  end
+end

data/test/test_parakeet_model.rb

@@ -0,0 +1,21 @@
+require_relative "helper"
+
+class TestParakeetModel < TestBase
+  def test_model
+    parakeet = Parakeet::Context.new("test/fixtures/for-tests-ggml-parakeet-tdt.bin")
+    assert_instance_of Parakeet::Model, parakeet.model
+  end
+
+  def test_attributes
+    parakeet = Parakeet::Context.new("test/fixtures/for-tests-ggml-parakeet-tdt.bin")
+    model = parakeet.model
+
+    assert_equal 10, model.n_vocab
+    assert_equal 3200, model.n_audio_ctx
+    assert_equal 8, model.n_audio_state
+    assert_equal 2, model.n_audio_head
+    assert_equal 1, model.n_audio_layer
+    assert_equal 16, model.n_mels
+    assert_equal 0, model.ftype
+  end
+end

data/test/test_parakeet_params.rb

@@ -0,0 +1,78 @@
+require_relative "helper"
+require "etc"
+
+class TestParakeetParams < TestBase
+  PARAM_NAMES = [
+    :n_threads,
+    :offset_ms,
+    :duration_ms,
+    :no_context,
+    :audio_ctx
+  ]
+
+  def setup
+    @params = Parakeet::Params.new
+  end
+
+  def test_new
+    assert_instance_of Parakeet::Params, @params
+  end
+
+  def test_n_threads
+    assert_equal [4, Etc.nprocessors].min, @params.n_threads
+
+    @params.n_threads = 1
+    assert_equal 1, @params.n_threads
+  end
+
+  def test_offset_ms
+    assert_equal 0, @params.offset_ms
+
+    @params.offset_ms = 10_000
+    assert_equal 10_000, @params.offset_ms
+  end
+
+  def test_duration_ms
+    assert_equal 0, @params.duration_ms
+
+    @params.duration_ms = 60_000
+    assert_equal 60_000, @params.duration_ms
+  end
+
+  def test_no_context
+    assert_equal true, @params.no_context
+
+    @params.no_context = false
+    assert_equal false, @params.no_context
+  end
+
+  def test_audio_ctx
+    assert_equal 0, @params.audio_ctx
+
+    @params.audio_ctx = 1
+    assert_equal 1, @params.audio_ctx
+  end
+
+  def test_new_with_kw_args
+    params = Parakeet::Params.new(n_threads: 1)
+    assert_equal 1, params.n_threads
+    assert_equal 0, params.offset_ms
+  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]
+              default_value + 1
+            end
+    params = Parakeet::Params.new(param => value)
+    assert_equal value, params.send(param)
+
+    PARAM_NAMES.reject {|name| name == param}.each do |name|
+      assert_equal @params.send(name), params.send(name)
+    end
+  end
+end

data/test/test_parakeet_segment.rb

@@ -0,0 +1,42 @@
+require_relative "helper"
+
+class TestParakeetSegment < TestBase
+  def setup
+    omit "Skip not to download large model" if ENV["CI"]
+
+    @parakeet = Parakeet::Context.new("parakeet-tdt-0.6b-v3-q4_0")
+    @parakeet.transcribe AUDIO, Parakeet::Params.new
+  end
+
+  def test_segment
+    whole_text = ""
+    @parakeet.each_segment do |segment|
+      assert_instance_of Parakeet::Segment, segment
+      assert_kind_of Integer, segment.start_time
+      assert segment.end_time >= segment.start_time
+      assert_kind_of String, segment.text
+      whole_text << segment.text
+    end
+    assert_match(/ask not what your country can do for you, ask what you can do for your country/, whole_text)
+  end
+
+  def test_deconstruct_keys
+    segment = @parakeet.each_segment.first
+    expected = {
+      start_time: segment.start_time,
+      end_time: segment.end_time,
+      text: segment.text
+    }
+    assert_equal expected, segment.deconstruct_keys([:start_time, :end_time, :text])
+  end
+
+  def test_deconstruct_keys_with_nil
+    segment = @parakeet.each_segment.first
+    expected = {
+      start_time: segment.start_time,
+      end_time: segment.end_time,
+      text: segment.text
+    }
+    assert_equal expected, segment.deconstruct_keys(nil)
+  end
+end

data/test/test_parakeet_token.rb

@@ -0,0 +1,73 @@
+require_relative "helper"
+
+class TestParakeetToken < TestBase
+  ATTRS = %i[
+    id
+    duration_idx
+    duration_value
+    frame_index
+    probability
+    log_probability
+    start_time
+    end_time
+    word_start?
+    text
+  ]
+
+  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
+    parakeet.transcribe AUDIO, params
+    @segment = parakeet.each_segment.first
+  end
+
+  def test_each_token
+    i = 0
+    @segment.each_token do |token|
+      i += 1
+      assert_instance_of Parakeet::Token, token
+    end
+    assert_equal 38, i
+  end
+
+  def test_each_token_without_block
+    assert_instance_of Enumerator, @segment.each_token
+  end
+
+  def test_token
+    token = @segment.each_token.first
+
+    assert_instance_of Parakeet::Token, token
+    assert_instance_of Integer, token.id
+    assert_instance_of Integer, token.duration_idx
+    assert_instance_of Integer, token.duration_value
+    assert_instance_of Integer, token.frame_index
+    assert_instance_of Float, token.probability
+    assert_instance_of Float, token.log_probability
+    assert_instance_of Integer, token.start_time
+    assert_instance_of Integer, token.end_time
+    assert_instance_of String, token.text
+  end
+
+  def test_text
+    assert_equal ["▁And", "▁so", ",", "▁my", "▁f", "ell", "ow", "▁Amer", "ic", "ans", ",", "▁a", "sk", "▁not", "▁what", "▁your", "▁co", "un", "tr", "y", "▁can", "▁do", "▁for", "▁you", ",", "▁a", "sk", "▁what", "▁you", "▁can", "▁do", "▁for", "▁your", "▁co", "un", "tr", "y", "."],
+                 @segment.each_token.collect(&:text)
+  end
+
+  def test_deconstruct_keys_with_nil
+    token = @segment.each_token.first
+    expected = ATTRS.collect {|attr| [attr.to_s.sub(/\?\z/, "").intern, token.send(attr)]}.to_h
+    assert_equal expected, token.deconstruct_keys(nil)
+  end
+
+  def test_deconstruct_keys_with_keys
+    token = @segment.each_token.first
+    expected = ATTRS.collect {|attr| [attr.to_s.sub(/\?\z/, "").intern, token.send(attr)]}.to_h
+    assert_equal expected, token.deconstruct_keys(expected.keys)
+  end
+end

data/test/test_params.rb

@@ -46,6 +46,8 @@ class TestParams < TestBase
   def test_language
     @params.language = "en"
     assert_equal @params.language, "en"
+    GC.compact
+    assert_equal @params.language, "en"
     @params.language = "auto"
     assert_equal @params.language, "auto"
   end

data/test/test_vad.rb

@@ -16,4 +16,13 @@ class TestVAD < TestBase
       assert_match(/ask not what your country can do for you[,.] ask what you can do for your country/i, text)
     end
   end
+
+  def test_vad_segments_api
+    @whisper.transcribe TestBase::AUDIO, @params
+
+    assert_equal 4, @whisper.full_n_vad_segments
+    @whisper.full_n_vad_segments.times do |i|
+      assert @whisper.full_get_vad_segment_t0(i) < @whisper.full_get_vad_segment_t1(i)
+    end
+  end
 end

data/test/test_vad_context.rb

@@ -44,8 +44,8 @@ class TestVADContext < TestBase
     assert_instance_of Enumerator, segments.each
 
     segment = segments.each.first
-    assert_instance_of Float, segment.start_time
-    assert_instance_of Float, segment.end_time
+    assert_instance_of Integer, segment.start_time
+    assert_instance_of Integer, segment.end_time
 
     segment => {start_time:, end_time:}
     assert_equal segment.start_time, start_time

data/test/test_vad_segment.rb

@@ -9,7 +9,7 @@ class TestVADSegment < TestBase
     end
 
     assert_raise do
-      segments.end_time
+      segment.end_time
     end
 
     assert_raise do