whispercpp 1.3.2 → 1.3.3

data/lib/whisper/context.rb

@@ -0,0 +1,15 @@
+module Whisper
+  class Context
+    def to_srt
+      each_segment.with_index.reduce("") {|srt, (segment, index)|
+        srt << "#{index + 1}\n#{segment.to_srt_cue}\n"
+      }
+    end
+
+    def to_webvtt
+      each_segment.with_index.reduce("WEBVTT\n\n") {|webvtt, (segment, index)|
+        webvtt << "#{index + 1}\n#{segment.to_webvtt_cue}\n"
+      }
+    end
+  end
+end

data/lib/whisper/model/uri.rb

@@ -130,6 +130,44 @@ module Whisper
       end
     end
 
+    class ZipURI < URI
+      def cache
+        zip_path = super
+        dest = unzipped_path
+        return if dest.exist? && dest.mtime >= zip_path.mtime
+        escaping dest do
+          system "unzip", "-q", "-d", zip_path.dirname.to_path, zip_path.to_path, exception: true
+        end
+        zip_path
+      end
+
+      def clear_cache
+        super
+        unzipped_path.rmtree if unzipped_path.exist?
+      end
+
+      private
+
+      def unzipped_path
+        cache_path.sub_ext("")
+      end
+
+      def escaping(path)
+        escaped = Pathname("#{path}.removing")
+        if path.exist?
+          escaped.rmtree if escaped.exist?
+          path.rename escaped
+        end
+        yield
+      ensure
+        if path.exist?
+          escaped.rmtree if escaped.exist?
+        else
+          escaped.rename path if escaped.exist?
+        end
+      end
+    end
+
     @pre_converted_models = %w[
       tiny
       tiny.en
@@ -171,8 +209,25 @@ module Whisper
       @pre_converted_models[name] = URI.new("https://huggingface.co/ggml-org/whisper-vad/resolve/main/ggml-#{name}.bin")
     end
 
+    @coreml_compiled_models = %w[
+      tiny
+      tiny.en
+      base
+      base.en
+      small
+      small.en
+      medium
+      medium.en
+      large-v1
+      large-v2
+      large-v3
+      large-v3-turbo
+    ].each_with_object({}) do |name, models|
+      models[@pre_converted_models[name]] = ZipURI.new("https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-#{name}-encoder.mlmodelc.zip")
+    end
+
     class << self
-      attr_reader :pre_converted_models
+      attr_reader :pre_converted_models, :coreml_compiled_models
     end
   end
 end

data/lib/whisper/segment.rb

@@ -0,0 +1,58 @@
+module Whisper
+  class Segment
+    SRT_ESCAPES = {
+      "&" => "&",
+      "<" => "&lt;",
+      ">" => "&gt;",
+    }
+    SRT_ESCAPES_RE = Regexp.union(SRT_ESCAPES.keys)
+    private_constant :SRT_ESCAPES, :SRT_ESCAPES_RE
+
+    def to_srt_cue
+      "#{srt_start_time} --> #{srt_end_time}\n#{srt_text}\n"
+    end
+
+    def to_webvtt_cue
+      "#{webvtt_start_time} --> #{webvtt_end_time}\n#{webvtt_text}\n"
+    end
+
+    private
+
+    def time_to_a(time)
+      sec, decimal_part = time.divmod(1000)
+      min, sec = sec.divmod(60)
+      hour, min = min.divmod(60)
+      [hour, min, sec, decimal_part]
+    end
+
+    def srt_time(time)
+      "%02d:%02d:%02d,%03d" % time_to_a(time)
+    end
+
+    def srt_start_time
+      srt_time(start_time)
+    end
+
+    def srt_end_time
+      srt_time(end_time)
+    end
+
+    def srt_text
+      text.gsub(SRT_ESCAPES_RE, SRT_ESCAPES)
+    end
+
+    def webvtt_time(time)
+      "%02d:%02d:%02d.%03d" % time_to_a(time)
+    end
+
+    def webvtt_start_time
+      webvtt_time(start_time)
+    end
+
+    def webvtt_end_time
+      webvtt_time(end_time)
+    end
+
+    alias webvtt_text srt_text
+  end
+end

data/sig/whisper.rbs

@@ -10,6 +10,7 @@ module Whisper
   type encoder_begin_callback = ^(Whisper::Context, void, Object user_data) -> void
   type abort_callback = ^(Whisper::Context, void, Object user_data) -> boolish
 
+  VERSION: String
   LOG_LEVEL_NONE: Integer
   LOG_LEVEL_INFO: Integer
   LOG_LEVEL_WARN: Integer
@@ -22,21 +23,22 @@ module Whisper
   def self.lang_str: (Integer id) -> String
   def self.lang_str_full: (Integer id) -> String
   def self.log_set: (log_callback, Object? user_data) -> log_callback
+  def self.system_info_str: () -> String
 
   class Context
-    def self.new: (path | ::URI::HTTP) -> instance
+    def self.new: (String | path | ::URI::HTTP) -> instance
 
     # transcribe a single file
     # can emit to a block results
     #
-    #   params = Whisper::Params.new
-    #   params.duration = 60_000
-    #   whisper.transcribe "path/to/audio.wav", params do |text|
-    #     puts text
-    #   end
+    #     params = Whisper::Params.new
+    #     params.duration = 60_000
+    #     whisper.transcribe "path/to/audio.wav", params do |text|
+    #       puts text
+    #     end
     #
-    def transcribe: (string, Params) -> self
-                  | (string, Params) { (String) -> void } -> self
+    def transcribe: (string, Params, ?n_processors: Integer) -> self
+                  | (string, Params, ?n_processors: Integer) { (String) -> void } -> self
 
     def model_n_vocab: () -> Integer
     def model_n_audio_ctx: () -> Integer
@@ -49,16 +51,16 @@ module Whisper
 
     # Yields each Whisper::Segment:
     #
-    #   whisper.transcribe("path/to/audio.wav", params)
-    #   whisper.each_segment do |segment|
-    #     puts segment.text
-    #   end
+    #     whisper.transcribe("path/to/audio.wav", params)
+    #     whisper.each_segment do |segment|
+    #       puts segment.text
+    #     end
     #
     # Returns an Enumerator if no block given:
     #
-    #   whisper.transcribe("path/to/audio.wav", params)
-    #   enum = whisper.each_segment
-    #   enum.to_a # => [#<Whisper::Segment>, ...]
+    #     whisper.transcribe("path/to/audio.wav", params)
+    #     enum = whisper.each_segment
+    #     enum.to_a # => [#<Whisper::Segment>, ...]
     #
     def each_segment: { (Segment) -> void } -> void
                     | () -> Enumerator[Segment]
@@ -73,25 +75,25 @@ module Whisper
 
     # Start time of a segment indexed by +segment_index+ in centiseconds (10 times milliseconds).
     #
-    #   full_get_segment_t0(3) # => 1668 (16680 ms)
+    #     full_get_segment_t0(3) # => 1668 (16680 ms)
     #
     def full_get_segment_t0: (Integer) -> Integer
 
     # End time of a segment indexed by +segment_index+ in centiseconds (10 times milliseconds).
     #
-    #   full_get_segment_t1(3) # => 1668 (16680 ms)
+    #     full_get_segment_t1(3) # => 1668 (16680 ms)
     #
     def full_get_segment_t1: (Integer) -> Integer
 
     # Whether the next segment indexed by +segment_index+ is predicated as a speaker turn.
     #
-    #   full_get_segment_speacker_turn_next(3) # => true
+    #     full_get_segment_speacker_turn_next(3) # => true
     #
     def full_get_segment_speaker_turn_next: (Integer) -> (true | false)
 
     # Text of a segment indexed by +segment_index+.
     #
-    #   full_get_segment_text(3) # => "ask not what your country can do for you, ..."
+    #     full_get_segment_text(3) # => "ask not what your country can do for you, ..."
     #
     def full_get_segment_text: (Integer) -> String
 
@@ -115,6 +117,9 @@ module Whisper
     def full_parallel: (Params, Array[Float], ?Integer n_samples) -> self
                      | (Params, _Samples, ?Integer n_samples) -> self
                      | (Params, _Samples, ?Integer? n_samples, Integer n_processors) -> self
+
+    def to_srt: () -> String
+    def to_webvtt: () -> String
   end
 
   class Params
@@ -281,9 +286,9 @@ module Whisper
 
     # Sets new segment callback, called for every newly generated text segment.
     #
-    #   params.new_segment_callback = ->(context, _, n_new, user_data) {
-    #     # ...
-    #   }
+    #     params.new_segment_callback = ->(context, _, n_new, user_data) {
+    #       # ...
+    #     }
     #
     def new_segment_callback=: (new_segment_callback) -> new_segment_callback
     def new_segment_callback: () -> (new_segment_callback | nil)
@@ -296,9 +301,9 @@ module Whisper
 
     # Sets progress callback, called on each progress update.
     #
-    #   params.new_segment_callback = ->(context, _, progress, user_data) {
-    #     # ...
-    #   }
+    #     params.new_segment_callback = ->(context, _, progress, user_data) {
+    #       # ...
+    #     }
     #
     # +progress+ is an Integer between 0 and 100.
     #
@@ -326,9 +331,9 @@ module Whisper
 
     # Sets abort callback, called to check if the process should be aborted.
     #
-    #   params.abort_callback = ->(user_data) {
-    #     # ...
-    #   }
+    #     params.abort_callback = ->(user_data) {
+    #       # ...
+    #     }
     #
     #
     def abort_callback=: (abort_callback) -> abort_callback
@@ -357,9 +362,9 @@ module Whisper
 
     # Hook called on new segment. Yields each Whisper::Segment.
     #
-    #   whisper.on_new_segment do |segment|
-    #     # ...
-    #   end
+    #     whisper.on_new_segment do |segment|
+    #       # ...
+    #     end
     #
     def on_new_segment: { (Segment) -> void } -> void
 
@@ -373,19 +378,20 @@ module Whisper
 
     # Call block to determine whether abort or not. Return +true+ when you want to abort.
     #
-    #   params.abort_on do
-    #     if some_condition
-    #       true # abort
-    #     else
-    #       false # continue
+    #     params.abort_on do
+    #       if some_condition
+    #         true # abort
+    #       else
+    #         false # continue
+    #       end
     #     end
-    #   end
     #
     def abort_on: { (Object user_data) -> boolish } -> void
   end
 
   class Model
     def self.pre_converted_models: () -> Hash[String, Model::URI]
+    def self.coreml_compiled_models: () -> Hash[Model::URI, Model::ZipURI]
     def self.new: () -> instance
     def n_vocab: () -> Integer
     def n_audio_ctx: () -> Integer
@@ -405,9 +411,22 @@ module Whisper
       def to_path: -> String
       def clear_cache: -> void
     end
+
+    class ZipURI < URI
+      def cache: () -> Pathname
+      def clear_cache: () -> void
+    end
   end
 
   class Segment
+    type deconstructed_keys = {
+      start_time: (Integer | nil),
+      end_time: (Integer | nil),
+      text: (String | nil),
+      no_speech_prob: (Float | nil),
+      speaker_turn_next: (true | false | nil)
+    }
+
     # Start time in milliseconds.
     #
     def start_time: () -> Integer
@@ -417,10 +436,21 @@ module Whisper
     def end_time: () -> Integer
 
     # Whether the next segment is predicted as a speaker turn.
-    def speaker_next_turn?: () -> (true | false)
+    def speaker_turn_next?: () -> (true | false)
 
     def text: () -> String
     def no_speech_prob: () -> Float
+    def to_srt_cue: () -> String
+    def to_webvtt_cue: () -> String
+
+    #  Possible keys: :start_time, :end_time, :text, :no_speech_prob, :speaker_turn_next
+    #
+    #      whisper.each_segment do |segment|
+    #        segment => {start_time:, end_time:, text:, no_speech_prob:, speaker_turn_next:}
+    #
+    #        puts "[#{start_time} --> #{end_time}] #{text} (no speech prob: #{no_speech_prob}#{speaker_turn_next ? ', speaker turns next' : ''})"
+    #      end
+    def deconstruct_keys: (Array[:start_time | :end_time | :text | :no_speech_prob | :speaker_turn_next] | nil) -> deconstructed_keys
   end
 
   module VAD

data/{tests → test}/helper.rb

@@ -3,7 +3,7 @@ require "whisper"
 require_relative "jfk_reader/jfk_reader"
 
 class TestBase < Test::Unit::TestCase
-  AUDIO = File.join(__dir__, "..", "..", "..", "samples", "jfk.wav")
+  AUDIO = File.join(__dir__, "fixtures", "jfk.wav")
 
   class << self
     def whisper
@@ -21,15 +21,4 @@ class TestBase < Test::Unit::TestCase
   def whisper
     self.class.whisper
   end
-
-  module BuildOptions
-    load "ext/options.rb", self
-    Options.include self
-
-    def enable_config(name)
-    end
-
-    def arg_config(name)
-    end
-  end
 end

data/{tests → test}/test_model.rb

@@ -106,4 +106,13 @@ class TestModel < TestBase
     assert_equal 1, model.ftype
     assert_equal "base", model.type
   end
+
+  def test_coreml_model_auto_download
+    uri = Whisper::Model.coreml_compiled_models[Whisper::Model.pre_converted_models["tiny"]]
+    model_path = Pathname(uri.to_path).sub_ext("")
+    model_path.rmtree if model_path.exist?
+
+    uri.cache
+    assert_path_exist model_path
+  end
 end

data/test/test_package.rb

@@ -0,0 +1,51 @@
+require_relative "helper"
+require 'tempfile'
+require 'tmpdir'
+require 'shellwords'
+
+class TestPackage < TestBase
+  def test_build
+    Tempfile.create do |file|
+      assert system("gem", "build", "whispercpp.gemspec", "--output", file.to_path.shellescape, exception: true)
+      assert file.size > 0
+      assert_path_exist file.to_path
+    end
+  end
+
+  sub_test_case "Building binary on installation" do
+    def setup
+      system "rake", "build", exception: true
+    end
+
+    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
+        assert_installed dir, gemspec.version
+      end
+    end
+
+    def test_install_with_coreml
+      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
+          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'`)
+        end
+      end
+    end
+
+    private
+
+    def assert_installed(dir, version)
+      assert_path_exist File.join(dir, "gems/whispercpp-#{version}/lib", "whisper.#{RbConfig::CONFIG["DLEXT"]}")
+      assert_path_exist File.join(dir, "gems/whispercpp-#{version}/LICENSE")
+      assert_path_not_exist File.join(dir, "gems/whispercpp-#{version}/ext/build")
+    end
+  end
+end

data/test/test_segment.rb

@@ -0,0 +1,146 @@
+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
+
+  def test_transcription_after_segment_retrieved
+    params = Whisper::Params.new
+    segment = whisper.each_segment.first
+    assert_match(/ask not what your country can do for you, ask what you can do for your country/, segment.text)
+
+    whisper.transcribe(AUDIO, Whisper::Params.new(offset: 5000))
+    assert_not_match(/ask not what your country can do for you, ask what you can do for your country/, segment.text)
+    assert_match(/what you can do for your country/i, segment.text)
+  end
+
+  def test_pattern_matching
+    segment = whisper.each_segment.first
+    segment => {start_time:, end_time:, text:, no_speech_prob:, speaker_turn_next:}
+
+    assert_equal segment.start_time, start_time
+    assert_equal segment.end_time, end_time
+    assert_equal segment.text, text
+    assert_equal segment.no_speech_prob, no_speech_prob
+    assert_equal segment.speaker_turn_next?, speaker_turn_next
+  end
+
+  def test_pattern_matching_partial
+    segment = whisper.each_segment.first
+    segment => {start_time:, end_time:, text:}
+
+    assert_equal segment.start_time, start_time
+    assert_equal segment.end_time, end_time
+    assert_equal segment.text, text
+  end
+
+  def test_deconstruct_keys
+    segment = whisper.each_segment.first
+    expected = {
+      start_time: segment.start_time,
+      end_time: segment.end_time,
+      text: segment.text,
+      no_speech_prob: segment.no_speech_prob,
+      speaker_turn_next: segment.speaker_turn_next?
+    }
+    assert_equal expected, segment.deconstruct_keys([:start_time, :end_time, :text, :no_speech_prob, :speaker_turn_next])
+  end
+
+  def test_deconstruct_keys_non_existent
+    omit "Undefined behavior"
+
+    segment = whisper.each_segment.first
+
+    assert_equal({}, segment.deconstruct_keys([:non_existent]))
+  end
+
+  def test_deconstruct_keys_too_many_keys
+    omit "Undefined behavior"
+
+    segment = whisper.each_segment.first
+
+    assert_equal({}, segment.deconstruct_keys([:start_time, :end_time, :text, :no_speech_prob, :speaker_turn_next, :extra_key]))
+  end
+
+  def test_deconstruct_keys_includes_non_existent_keys_not_too_many
+    omit "Undefined behavior"
+
+    segment = whisper.each_segment.first
+
+    expected = {
+      start_time: segment.start_time,
+      end_time: segment.end_time,
+      text: segment.text,
+      no_speech_prob: segment.no_speech_prob
+    }
+    assert_equal(expected, segment.deconstruct_keys([:start_time, :end_time, :text, :no_speech_prob, :non_existent]))
+  end
+end

data/{tests → test}/test_whisper.rb

@@ -20,6 +20,24 @@ class TestWhisper < TestBase
     }
   end
 
+  def test_transcribe_non_parallel
+    @whisper = Whisper::Context.new("base.en")
+    params  = Whisper::Params.new
+
+    @whisper.transcribe(AUDIO, params, n_processors: 1) {|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_n_processors
+    @whisper = Whisper::Context.new("base.en")
+    params  = Whisper::Params.new
+
+    @whisper.transcribe(AUDIO, params, n_processors: 4) {|text|
+      assert_match(/ask not what your country can do for you[,.] ask what you can do for your country/i, text)
+    }
+  end
+
   sub_test_case "After transcription" do
     def test_full_n_segments
       assert_equal 1, whisper.full_n_segments
@@ -94,6 +112,14 @@ class TestWhisper < TestBase
     end
   end
 
+  def test_system_info_str
+    assert_match(/\AWHISPER : COREML = \d | OPENVINO = \d |/, Whisper.system_info_str)
+  end
+
+  def test_version
+    assert_kind_of String, Whisper::VERSION
+  end
+
   def test_log_set
     user_data = Object.new
     logs = []
@@ -223,4 +249,48 @@ class TestWhisper < TestBase
       assert_match(/for your country/i, text)
     end
   end
+
+  def test_to_srt
+    whisper = Whisper::Context.new("base.en")
+    whisper.transcribe AUDIO, @params
+
+    lines = whisper.to_srt.lines
+    assert_match(/\A\d+\n/, lines[0])
+    assert_match(/\d{2}:\d{2}:\d{2},\d{3} --> \d{2}:\d{2}:\d{2},\d{3}\n/, lines[1])
+    assert_match(/ask not what your country can do for you, ask what you can do for your country/, lines[2])
+  end
+
+  def test_to_webvtt
+    whisper = Whisper::Context.new("base.en")
+    whisper.transcribe AUDIO, @params
+
+    lines = whisper.to_webvtt.lines
+    assert_equal "WEBVTT\n", lines[0]
+    assert_equal "\n", lines[1]
+    assert_match(/\A\d+\n/, lines[2])
+    assert_match(/\d{2}:\d{2}:\d{2}\.\d{3} --> \d{2}:\d{2}:\d{2}\.\d{3}\n/, lines[3])
+    assert_match(/ask not what your country can do for you, ask what you can do for your country/, lines[4])
+  end
+
+  sub_test_case "Format needs escape" do
+    def setup
+      @whisper = Whisper::Context.new("base.en")
+      @whisper.transcribe AUDIO, Whisper::Params.new
+      segment = @whisper.each_segment.first
+      segment.define_singleton_method :text do
+        "& so my fellow Americans --> ask not what your country can do for you <-- ask what you can do for your country."
+      end
+      @whisper.define_singleton_method :each_segment do
+        Enumerator.new(3) {|yielder| 3.times {yielder << segment}}
+      end
+    end
+
+    def test_to_srt_escape
+      assert_equal "&amp; so my fellow Americans --&gt; ask not what your country can do for you &lt;-- ask what you can do for your country.\n", @whisper.to_srt.lines[2]
+    end
+
+    def test_to_webvtt_escape
+      assert_equal "&amp; so my fellow Americans --&gt; ask not what your country can do for you &lt;-- ask what you can do for your country.\n", @whisper.to_webvtt.lines[4]
+    end
+  end
 end