ruby : add VAD::Context#segments_from_samples, allow Pathname, etc. (#3633)

* ruby : Bump version to 1.3.6

* Fix code in example

* Add sample code to transcribe from MemoryView

* Define GetVADContext macro

* Use GetVADContext

* Extract parse_full_args function

* Use parse_full_args in ruby_whisper_full_parallel

* Free samples after use

* Check return value of parse_full_args()

* Define GetVADParams macro

* Add VAD::Context#segments_from_samples

* Add tests for VAD::Context#segments_from_samples

* Add signature for VAD::Context#segments_from_samples

* Add sample code for VAD::Context#segments_from_samples

* Add test for Whisper::Context#transcribe with Pathname

* Make Whisper::Context#transcribe and Whisper::VAD::Context#detect accept Pathname

* Update signature of Whisper::Context#transcribe

* Fix variable name

* Don't free memory view

* Make parse_full_args return struct

* Fallback when failed to get MemoryView

* Add num of samples when too long

* Check members of MemoryView

* Fix a typo

* Remove unnecessary include

* Fix a typo

* Fix a typo

* Care the case of MemoryView doesn't fit spec

* Add TODO comment

* Add optimazation option to compiler flags

* Use ALLOC_N instead of malloc

* Add description to sample code

* Rename and change args: parse_full_args -> parse_samples

* Free samples when exception raised

* Assign type check result to a variable

* Define wrapper function of whisper_full

* Change signature of parse_samples for rb_ensure

* Ensure release MemoryView

* Extract fill_samples function

* Free samples memory when filling it failed

* Free samples memory when transcription failed

* Prepare transcription in wrapper funciton

* Change function name

* Simplify function boundary

bindings/ruby/test/test_vad_context.rb

@@ -9,6 +9,25 @@ class TestVADContext < TestBase
   def test_detect
     context = Whisper::VAD::Context.new("silero-v6.2.0")
     segments = context.detect(AUDIO, Whisper::VAD::Params.new)
+    assert_segments segments
+  end
+
+  def test_invalid_model_type
+    assert_raise TypeError do
+      Whisper::VAD::Context.new(Object.new)
+    end
+  end
+
+  def test_allocate
+    vad = Whisper::VAD::Context.allocate
+    assert_raise do
+      vad.detect(AUDIO, Whisper::VAD::Params.new)
+    end
+  end
+
+  private
+
+  def assert_segments(segments)
     assert_instance_of Whisper::VAD::Segments, segments
 
     i = 0
@@ -35,16 +54,47 @@ class TestVADContext < TestBase
     assert_equal 4, segments.length
   end
 
-  def test_invalid_model_type
-    assert_raise TypeError do
-      Whisper::VAD::Context.new(Object.new)
+  sub_test_case "from samples" do
+    def setup
+      super
+      @vad = Whisper::VAD::Context.new("silero-v6.2.0")
+      @samples = File.read(AUDIO, nil, 78).unpack("s<*").collect {|i| i.to_f / 2**15}
     end
-  end
 
-  def test_allocate
-    vad = Whisper::VAD::Context.allocate
-    assert_raise do
-      vad.detect(AUDIO, Whisper::VAD::Params.new)
+    def test_segments_from_samples
+      segments = @vad.segments_from_samples(Whisper::VAD::Params.new, @samples, @samples.length)
+      assert_segments segments
+    end
+
+    def test_segments_from_samples_without_length
+      segments = @vad.segments_from_samples(Whisper::VAD::Params.new, @samples)
+      assert_segments segments
+    end
+
+    def test_segments_from_samples_enumerator
+      samples = @samples.each
+      segments = @vad.segments_from_samples(Whisper::VAD::Params.new, samples, @samples.length)
+      assert_segments segments
+    end
+
+    def test_segments_from_samples_enumerator_without_length
+      samples = @samples.each
+      assert_raise ArgumentError do
+        @vad.segments_from_samples(Whisper::VAD::Params.new, samples)
+      end
+    end
+
+    def test_segments_from_samples_enumerator_with_too_large_length
+      samples = @samples.each.take(10).to_enum
+      assert_raise StopIteration do
+        @vad.segments_from_samples(Whisper::VAD::Params.new, samples, 11)
+      end
+    end
+
+    def test_segments_from_samples_with_memory_view
+      samples = JFKReader.new(AUDIO)
+      segments = @vad.segments_from_samples(Whisper::VAD::Params.new, samples)
+      assert_segments segments
     end
   end
 end

bindings/ruby/test/test_whisper.rb

@@ -1,6 +1,7 @@
 require_relative "helper"
 require "stringio"
 require "etc"
+require "pathname"
 
 # Exists to detect memory-related bug
 Whisper.log_set ->(level, buffer, user_data) {}, nil
@@ -20,6 +21,15 @@ class TestWhisper < TestBase
     }
   end
 
+  def test_whisper_pathname
+    @whisper = Whisper::Context.new("base.en")
+    params  = Whisper::Params.new
+
+    @whisper.transcribe(Pathname(AUDIO), params) {|text|
+      assert_match(/ask not what your country can do for you, ask what you can do for your country/, text)
+    }
+  end
+
   def test_transcribe_non_parallel
     @whisper = Whisper::Context.new("base.en")
     params  = Whisper::Params.new
@@ -207,6 +217,16 @@ class TestWhisper < TestBase
       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_with_memroy_view_gc
+      samples = JFKReader.new(AUDIO)
+      @whisper.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
+
     def test_full_parallel
       nprocessors = 2
       @whisper.full_parallel(@params, @samples, @samples.length, nprocessors)