whispercpp 1.3.2 → 1.3.4

data/ext/sources/tests/CMakeLists.txt

@@ -93,6 +93,9 @@ set(VAD_TEST test-vad)
 add_executable(${VAD_TEST} ${VAD_TEST}.cpp)
 target_include_directories(${VAD_TEST} PRIVATE ../include ../ggml/include ../examples)
 target_link_libraries(${VAD_TEST} PRIVATE common)
+target_compile_definitions(${VAD_TEST} PRIVATE
+    VAD_MODEL_PATH="${PROJECT_SOURCE_DIR}/models/for-tests-silero-v5.1.2-ggml.bin"
+    SAMPLE_PATH="${PROJECT_SOURCE_DIR}/samples/jfk.wav")
 add_test(NAME ${VAD_TEST} COMMAND ${VAD_TEST})
 set_tests_properties(${VAD_TEST} PROPERTIES LABELS "unit")
 
@@ -101,5 +104,9 @@ set(VAD_TEST test-vad-full)
 add_executable(${VAD_TEST} ${VAD_TEST}.cpp)
 target_include_directories(${VAD_TEST} PRIVATE ../include ../ggml/include ../examples)
 target_link_libraries(${VAD_TEST} PRIVATE common)
+target_compile_definitions(${VAD_TEST} PRIVATE
+    WHISPER_MODEL_PATH="${PROJECT_SOURCE_DIR}/models/ggml-base.en.bin"
+    VAD_MODEL_PATH="${PROJECT_SOURCE_DIR}/models/for-tests-silero-v5.1.2-ggml.bin"
+    SAMPLE_PATH="${PROJECT_SOURCE_DIR}/samples/jfk.wav")
 add_test(NAME ${VAD_TEST} COMMAND ${VAD_TEST})
-set_tests_properties(${VAD_TARGET} PROPERTIES LABELS "base;en")
+set_tests_properties(${VAD_TEST} PROPERTIES LABELS "base;en")

data/ext/sources/tests/test-vad-full.cpp

@@ -13,9 +13,9 @@
 #include <cassert>
 
 int main() {
-    std::string whisper_model_path = "../../models/ggml-base.en.bin";
-    std::string vad_model_path     = "../../models/for-tests-silero-v5.1.2-ggml.bin";
-    std::string sample_path        = "../../samples/jfk.wav";
+    std::string whisper_model_path = WHISPER_MODEL_PATH;
+    std::string vad_model_path     = VAD_MODEL_PATH;
+    std::string sample_path        = SAMPLE_PATH;
 
     // Load the sample audio file
     std::vector<float> pcmf32;

data/ext/sources/tests/test-vad.cpp

@@ -48,8 +48,8 @@ struct whisper_vad_segments * test_detect_timestamps(
 }
 
 int main() {
-    std::string vad_model_path = "../../models/for-tests-silero-v5.1.2-ggml.bin";
-    std::string sample_path    = "../../samples/jfk.wav";
+    std::string vad_model_path = VAD_MODEL_PATH;
+    std::string sample_path    = SAMPLE_PATH;
 
     // Load the sample audio file
     std::vector<float> pcmf32;

data/extsources.rb

@@ -1,5 +1,10 @@
+require "pathname"
+
+root = Pathname("..")/".."
 ignored_dirs = %w[
   .devops
+  .github
+  ci
   examples/wchess/wchess.wasm
   examples/whisper.android
   examples/whisper.android.java
@@ -9,7 +14,7 @@ ignored_dirs = %w[
   models
   samples
   scripts
-]
+].collect {|dir| root/dir}
 ignored_files = %w[
   AUTHORS
   Makefile
@@ -17,18 +22,19 @@ ignored_files = %w[
   README_sycl.md
   .gitignore
   .gitmodules
+  .dockerignore
   whisper.nvim
   twitch.sh
   yt-wsp.sh
+  close-issue.yml
 ]
 
 EXTSOURCES =
-  `git ls-files -z ../..`.split("\x0")
-    .select {|file|
-      basename = File.basename(file)
-
-      ignored_dirs.all? {|dir| !file.start_with?("../../#{dir}")} &&
-        !ignored_files.include?(basename) &&
-        (file.start_with?("../..") || file.start_with?("../javascript")) &&
-        (!file.start_with?("../../.github/") || basename == "bindings-ruby.yml")
+  `git ls-files -z #{root}`.split("\x0")
+    .collect {|file| Pathname(file)}
+    .reject {|file|
+      ignored_dirs.any? {|dir| file.descend.any? {|desc| desc == dir}} ||
+        ignored_files.include?(file.basename.to_path) ||
+        (file.descend.to_a[1] != root && file.descend.to_a[1] != Pathname("..")/"javascript")
     }
+    .collect(&:to_path)

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

@@ -94,7 +94,7 @@ module Whisper
       end
 
       def show_progress(current, size)
-        progress_rate_available = size && $stderr.tty?
+        progress_rate_available = size && $stderr.tty? && $stderr.winsize[1] >= line.size
 
         unless @prev
           @prev = Time.now
@@ -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
@@ -130,6 +135,7 @@ module Whisper
       ?suppress_blank: boolish,
       ?suppress_nst: boolish,
       ?token_timestamps: boolish,
+      ?max_len: Integer,
       ?split_on_word: boolish,
       ?initial_prompt: string | nil,
       ?diarize: boolish,
@@ -217,6 +223,12 @@ module Whisper
     #
     def token_timestamps: () -> (true | false)
 
+    def max_len=: (Integer) -> Integer
+
+    # max segment length in characters.
+    #
+    def max_len: () -> Integer
+
     def split_on_word=: (boolish) -> boolish
 
     # If true, split on word rather than on token (when used with max_len).
@@ -281,9 +293,9 @@ 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 +308,9 @@ 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 +338,9 @@ 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 +369,9 @@ 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 +385,20 @@ 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 +418,22 @@ 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 +443,21 @@ 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/{tests → test}/test_params.rb

@@ -13,6 +13,7 @@ class TestParams < TestBase
     :suppress_blank,
     :suppress_nst,
     :token_timestamps,
+    :max_len,
     :split_on_word,
     :initial_prompt,
     :diarize,
@@ -139,6 +140,13 @@ class TestParams < TestBase
     assert !@params.token_timestamps
   end
 
+  def test_max_len
+    @params.max_len = 42
+    assert_equal @params.max_len, 42
+    @params.max_len = 0
+    assert_equal @params.max_len, 0
+  end
+
   def test_split_on_word
     @params.split_on_word = true
     assert @params.split_on_word