whispercpp 1.3.1 → 1.3.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 7f2881876a07bc3fb34dd40c70ca1cbd19688fc84f06a29dfb9abbcfd8108123
-  data.tar.gz: fae6462838866de9536a06c49ecc1b71fbaa2958862b47c42c4c0aafca363a86
+  metadata.gz: f3fdcc54e3e57a80116d06cd42636f910885f6e463387950414af3181ce956f6
+  data.tar.gz: de739103554359ce18d07666399670602fd1cbb62a0991352d32e9d625a4678e
 SHA512:
-  metadata.gz: c33d12da562d02202d576de93aebce6aa405eeb72abe961bec68745fb76ed7fc9ab7778e7f6284f13185de1e8c65c490893ad86844441f7059383e24e0624bb8
-  data.tar.gz: af9a88eb60abbfa3d77d3cfdb444dde5f07aab5a255771f348a279bce2920f34ff10a949be30ba3d77e3bb939935b0b8cca577d5cc97da83e6ece641d2fa7343
+  metadata.gz: e1ffb0f1b2874cf5cc210df61eaa9f8b716639c05b6bd05cc3e94abea0fc46544b15b7ed2ee8a251014f56da89af029bfaa105f8d52ae93372e64018e7c93ebd
+  data.tar.gz: 591eae5d183c25a37911a233020f1aaa5826734b4259443bb4c9f5bc7d061ace06095504a5b7426f3c9a5e43eab29c5c630b6ad51d6b4dc3c315596fb1a37114

data/.gitignore

@@ -1,5 +1,9 @@
 LICENSE
 pkg/
-lib/whisper.so
-lib/whisper.bundle
-lib/whisper.dll
+lib/whisper.*
+ext/examples/
+ext/ggml/
+ext/include/
+ext/scripts/
+ext/src/
+test/fixtures/

data/README.md

@@ -16,6 +16,32 @@ If bundler is not being used to manage dependencies, install the gem by executin
 
     $ gem install whispercpp
 
+You can pass build options for whisper.cpp, for instance:
+
+    $ bundle config build.whispercpp --enable-ggml-cuda
+
+or,
+
+    $ gem install whispercpp -- --enable-ggml-cuda
+
+See whisper.cpp's [README](https://github.com/ggml-org/whisper.cpp/blob/master/README.md) for available options. You need convert options present the README to Ruby-style options, for example:
+
+Boolean options:
+
+* `-DGGML_BLAS=1` -> `--enable-ggml-blas`
+* `-DWHISER_COREML=OFF` -> `--disable-whisper-coreml`
+
+Argument options:
+
+* `-DGGML_CUDA_COMPRESSION_MODE=size` -> `--ggml-cuda-compression-mode=size`
+
+Combination:
+
+* `-DGGML_CUDA=1 -DCMAKE_CUDA_ARCHITECTURES="86"` -> `--enable-ggml-cuda --cmake_cuda-architectures="86"`
+
+For boolean options like `GGML_CUDA`, the README says `-DGGML_CUDA=1`. You need strip `-D`, prepend `--enable-` for `1` or `ON` (`--disable-` for `0` or `OFF`) and make it kebab-case: `--enable-ggml-cuda`.  
+For options which require arguments like `CMAKE_CUDA_ARCHITECTURES`, the README says `-DCMAKE_CUDA_ARCHITECTURES="86"`. You need strip `-D`, prepend `--`, make it kebab-case, append `=` and append argument: `--cmake-cuda-architectures="86"`.
+
 Usage
 -----
 
@@ -24,14 +50,15 @@ require "whisper"
 
 whisper = Whisper::Context.new("base")
 
-params = Whisper::Params.new
-params.language = "en"
-params.offset = 10_000
-params.duration = 60_000
-params.max_text_tokens = 300
-params.translate = true
-params.print_timestamps = false
-params.initial_prompt = "Initial prompt here."
+params = Whisper::Params.new(
+  language: "en",
+  offset: 10_000,
+  duration: 60_000,
+  max_text_tokens: 300,
+  translate: true,
+  print_timestamps: false,
+  initial_prompt: "Initial prompt here."
+)
 
 whisper.transcribe("path/to/audio.wav", params) do |whole_text|
   puts whole_text
@@ -43,27 +70,16 @@ end
 
 Some models are prepared up-front:
 
-```ruby
-base_en = Whisper::Model.pre_converted_models["base.en"]
-whisper = Whisper::Context.new(base_en)
-```
-
-At first time you use a model, it is downloaded automatically. After that, downloaded cached file is used. To clear cache, call `#clear_cache`:
-
-```ruby
-Whisper::Model.pre_converted_models["base"].clear_cache
-```
-
 You also can use shorthand for pre-converted models:
 
 ```ruby
 whisper = Whisper::Context.new("base.en")
 ```
 
-You can see the list of prepared model names by `Whisper::Model.preconverted_models.keys`:
+You can see the list of prepared model names by `Whisper::Model.pre_converted_models.keys`:
 
 ```ruby
-puts Whisper::Model.preconverted_model_names
+puts Whisper::Model.pre_converted_models.keys
 # tiny
 # tiny.en
 # tiny-q5_1
@@ -78,6 +94,19 @@ puts Whisper::Model.preconverted_model_names
 #   :
 ```
 
+You can also retrieve each model:
+
+```ruby
+base_en = Whisper::Model.pre_converted_models["base.en"]
+whisper = Whisper::Context.new(base_en)
+```
+
+At first time you use a model, it is downloaded automatically. After that, downloaded cached file is used. To clear cache, call `#clear_cache`:
+
+```ruby
+Whisper::Model.pre_converted_models["base"].clear_cache
+```
+
 You can also use local model files you prepared:
 
 ```ruby
@@ -87,8 +116,9 @@ whisper = Whisper::Context.new("path/to/your/model.bin")
 Or, you can download model files:
 
 ```ruby
-model_uri = Whisper::Model::URI.new("http://example.net/uri/of/your/model.bin")
-whisper = Whisper::Context.new(model_uri)
+whisper = Whisper::Context.new("https://example.net/uri/of/your/model.bin")
+# Or
+whisper = Whisper::Context.new(URI("https://example.net/uri/of/your/model.bin"))
 ```
 
 See [models][] page for details.
@@ -97,9 +127,80 @@ See [models][] page for details.
 
 Currently, whisper.cpp accepts only 16-bit WAV files.
 
+### Voice Activity Detection (VAD) ###
+
+Support for Voice Activity Detection (VAD) can be enabled by setting `Whisper::Params`'s `vad` argument to `true` and specifying VAD model:
+
+```ruby
+Whisper::Params.new(
+  vad: true,
+  vad_model_path: "silero-v5.1.2",
+  # other arguments...
+)
+```
+
+When you pass the model name (`"silero-v5.1.2"`) or URI (`https://huggingface.co/ggml-org/whisper-vad/resolve/main/ggml-silero-v5.1.2.bin`), it will be downloaded automatically.
+Currently, "silero-v5.1.2" is registered as pre-converted model like ASR models. You also specify file path or URI of model.
+
+If you need configure VAD behavior, pass params for that:
+
+```ruby
+Whisper::Params.new(
+  vad: true,
+  vad_model_path: "silero-v5.1.2",
+  vad_params: Whisper::VAD::Params.new(
+    threshold: 1.0, # defaults to 0.5
+    min_speech_duration_ms: 500, # defaults to 250
+    min_silence_duration_ms: 200, # defaults to 100
+    max_speech_duration_s: 30000, # default is FLT_MAX,
+    speech_pad_ms: 50, # defaults to 30
+    samples_overlap: 0.5 # defaults to 0.1
+  ),
+  # other arguments...
+)
+```
+
+For details on VAD, see [whisper.cpp's README](https://github.com/ggml-org/whisper.cpp?tab=readme-ov-file#voice-activity-detection-vad).
+
+### Output ###
+
+whispercpp supports SRT and WebVTT output:
+
+```ruby
+puts whisper.transcribe("path/to/audio.wav", Whisper::Params.new).to_webvtt
+# =>
+WEBVTT
+
+1
+00:00:00.000 --> 00:00:03.860
+ My thought I have nobody by a beauty and will as you poured.
+
+2
+00:00:03.860 --> 00:00:09.840
+ Mr. Rochester is sub in that so-don't find simplest, and devoted about, to let might in
+
+3
+00:00:09.840 --> 00:00:09.940
+ a
+
+```
+
+You may call `#to_srt`, too
+
+
 API
 ---
 
+### Transcription ###
+
+By default, `Whisper::Context#transcribe` works in a single thread. You can make it work in parallel by passing `n_processors` option:
+
+```ruby
+whisper.transcribe("path/to/audio.wav", params, n_processors: Etc.nprocessors)
+```
+
+Note that transcription occasionally might be low accuracy when it works in parallel.
+
 ### Segments ###
 
 Once `Whisper::Context#transcribe` called, you can retrieve segments by `#each_segment`:
@@ -112,18 +213,18 @@ def format_time(time_ms)
   "%02d:%02d:%02d.%03d" % [hour, min, sec, decimal_part]
 end
 
-whisper.transcribe("path/to/audio.wav", params)
-
-whisper.each_segment.with_index do |segment, index|
-  line = "[%{nth}: %{st} --> %{ed}] %{text}" % {
-    nth: index + 1,
-    st: format_time(segment.start_time),
-    ed: format_time(segment.end_time),
-    text: segment.text
-  }
-  line << " (speaker turned)" if segment.speaker_next_turn?
-  puts line
-end
+whisper
+  .transcribe("path/to/audio.wav", params)
+  .each_segment.with_index do |segment, index|
+    line = "[%{nth}: %{st} --> %{ed}] %{text}" % {
+      nth: index + 1,
+      st: format_time(segment.start_time),
+      ed: format_time(segment.end_time),
+      text: segment.text
+    }
+    line << " (speaker turned)" if segment.speaker_turn_next?
+    puts line
+  end
 
 ```
 
@@ -137,7 +238,7 @@ params.on_new_segment do |segment|
     ed: format_time(segment.end_time),
     text: segment.text
   }
-  line << " (speaker turned)" if segment.speaker_next_turn?
+  line << " (speaker turned)" if segment.speaker_turn_next?
   puts line
 end
 
@@ -214,18 +315,35 @@ reader = WaveFile::Reader.new("path/to/audio.wav", WaveFile::Format.new(:mono, :
 samples = reader.enum_for(:each_buffer).map(&:samples).flatten
 
 whisper = Whisper::Context.new("base")
-whisper.full(Whisper::Params.new, samples)
-whisper.each_segment do |segment|
-  puts segment.text
-end
+whisper
+  .full(Whisper::Params.new, samples)
+  .each_segment do |segment|
+    puts segment.text
+  end
 ```
 
-The second argument `samples` may be an array, an object with `length` method, or a MemoryView. If you can prepare audio data as C array and export it as a MemoryView, whispercpp accepts and works with it with zero copy.
+The second argument `samples` may be an array, an object with `length` and `each` method, or a MemoryView. If you can prepare audio data as C array and export it as a MemoryView, whispercpp accepts and works with it with zero copy.
+
+Development
+-----------
+
+    % git clone https://github.com/ggml-org/whisper.cpp.git
+    % cd whisper.cpp/bindings/ruby
+    % rake test
+
+First call of `rake test` builds an extension and downloads a model for testing. After that, you add tests in `tests` directory and modify `ext/ruby_whisper.cpp`.
+
+If something seems wrong on build, running `rake clean` solves some cases.
+
+### Need help ###
+
+* Windows support
+* Refinement of C/C++ code, especially memory management
 
 License
 -------
 
 The same to [whisper.cpp][].
 
-[whisper.cpp]: https://github.com/ggerganov/whisper.cpp
-[models]: https://github.com/ggerganov/whisper.cpp/tree/master/models
+[whisper.cpp]: https://github.com/ggml-org/whisper.cpp
+[models]: https://github.com/ggml-org/whisper.cpp/tree/master/models

data/Rakefile

@@ -3,11 +3,15 @@ require "bundler/gem_tasks"
 require "rake/testtask"
 require_relative "extsources"
 
+SOURCES_DIR = "ext/sources"
+
 SOURCES = FileList[]
 
 EXTSOURCES.each do |src|
   basename = src.pathmap("%f")
-  dest = basename == "LICENSE" ? basename : src.pathmap("%{../..,ext}p")
+  dest = basename == "LICENSE" ? basename
+                               : src.pathmap("%{\\.\\./\\.\\.,#{SOURCES_DIR}}p")
+                                    .pathmap("%{\\.\\./javascript,#{SOURCES_DIR}/bindings/javascript}p")
   dir = dest.pathmap("%d")
   file src
   directory dir
@@ -18,9 +22,10 @@ EXTSOURCES.each do |src|
 end
 
 CLEAN.include SOURCES
-CLEAN.include FileList["ext/*.o", "ext/*.metal", "ext/whisper.{so,bundle,dll}"]
 
-task build: ["ext/Makefile", "ext/ruby_whisper.h", "ext/ruby_whisper.cpp", "whispercpp.gemspec"]
+SRC = FileList["ext/*.{c,cpp,h}"]
+
+task build: SOURCES
 
 directory "pkg"
 CLOBBER.include "pkg"
@@ -29,14 +34,28 @@ LIB_NAME = "whisper".ext(RbConfig::CONFIG["DLEXT"])
 SO_FILE = File.join("ext", LIB_NAME)
 LIB_FILE = File.join("lib", LIB_NAME)
 
-file "ext/Makefile" => ["ext/extconf.rb", "ext/ruby_whisper.h", "ext/ruby_whisper.cpp"] + SOURCES do |t|
-  Dir.chdir "ext" do
+file "ext/Makefile" => SRC + ["ext/extconf.rb"] + SOURCES do |t|
+  chdir "ext" do
     ruby "extconf.rb"
   end
 end
+if File.exist? "ext/Makefile"
+  task :make_clean do
+    cd "ext" do
+      sh "make", "clean"
+    end
+  end
+  task clean: :make_clean
+  task :make_distclean do
+    cd "ext" do
+      sh "make", "distclean"
+    end
+  end
+  task clobber: :make_distclean
+end
 
 file SO_FILE => "ext/Makefile" do |t|
-  Dir.chdir "ext" do
+  chdir "ext" do
     sh "make"
   end
 end
@@ -48,17 +67,30 @@ file LIB_FILE => [SO_FILE, "lib"] do |t|
 end
 CLEAN.include LIB_FILE
 
-Rake::TestTask.new do |t|
-  t.test_files = FileList["tests/test_*.rb"]
+Rake::TestTask.new
+
+TEST_FIXTURE_AUDIO = "test/fixtures/jfk.wav"
+TEST_FIXTURE_AUDIO_SRC = File.expand_path(File.join(__dir__, "..", "..", "samples", "jfk.wav"))
+TEST_FIXTURE_AUDIO_DIR = TEST_FIXTURE_AUDIO.pathmap("%d")
+directory TEST_FIXTURE_AUDIO_DIR
+if File.exist? TEST_FIXTURE_AUDIO_SRC
+  file TEST_FIXTURE_AUDIO => [TEST_FIXTURE_AUDIO_SRC, TEST_FIXTURE_AUDIO_DIR] do |t|
+    symlink t.source, t.name
+  end
+else
+  require "open-uri"
+  file TEST_FIXTURE_AUDIO => TEST_FIXTURE_AUDIO_DIR do |t|
+    File.write t.name, URI("https://github.com/ggml-org/whisper.cpp/raw/refs/heads/master/samples/jfk.wav").read
+  end
 end
 
-TEST_MEMORY_VIEW = "tests/jfk_reader/jfk_reader.#{RbConfig::CONFIG['DLEXT']}"
-file TEST_MEMORY_VIEW => "tests/jfk_reader/jfk_reader.c" do |t|
-  Dir.chdir "tests/jfk_reader" do
+TEST_MEMORY_VIEW = "test/jfk_reader/jfk_reader.#{RbConfig::CONFIG['DLEXT']}"
+file TEST_MEMORY_VIEW => "test/jfk_reader/jfk_reader.c" do |t|
+  chdir "test/jfk_reader" do
     ruby "extconf.rb"
     sh "make"
   end
 end
-CLEAN.include "tests/jfk_reader/jfk_reader.{o,#{RbConfig::CONFIG['DLEXT']}}"
+CLEAN.include TEST_MEMORY_VIEW
 
-task test: [LIB_FILE, TEST_MEMORY_VIEW]
+task test: [LIB_FILE, TEST_MEMORY_VIEW, TEST_FIXTURE_AUDIO]

data/ext/.gitignore

@@ -2,12 +2,8 @@ Makefile
 whisper.so
 whisper.bundle
 whisper.dll
-scripts/get-flags.mk
 *.o
-*.c
-*.cpp
-*.h
-*.m
-*.metal
-!ruby_whisper.cpp
-!ruby_whisper.h
+*.a
+sources/*
+!sources/CMakeGraphVizOptions.cmake
+mkmf.log

data/ext/dependencies.rb

@@ -0,0 +1,73 @@
+require "tsort"
+
+class Dependencies
+  include TSort
+
+  def initialize(cmake, options)
+    @cmake = cmake
+    @options = options
+    @static_lib_shape = nil
+    @nodes = {}
+    @graph = Hash.new {|h, k| h[k] = []}
+
+    generate_dot
+    parse_dot
+  end
+
+  def libs
+    tsort.filter_map {|node|
+      label, shape = @nodes[node]
+      if shape == @static_lib_shape
+        label.gsub(/\\n\([^)]+\)/, '')
+      else
+        nil
+      end
+    }.reverse.collect {|lib| "lib#{lib}.a"}
+  end
+
+  def to_s
+    libs.join(" ")
+  end
+
+  private
+
+  def dot_path
+    File.join(__dir__, "build", "whisper.cpp.dot")
+  end
+
+  def generate_dot
+    args = ["-S", "sources", "-B", "build", "--graphviz", dot_path, "-D", "BUILD_SHARED_LIBS=OFF"]
+    args << @options.to_s unless @options.to_s.empty?
+    system @cmake, *args, exception: true
+  end
+
+  def parse_dot
+    File.open(dot_path).each_line do |line|
+      case line
+      when /\[\s*label\s*=\s*"Static Library"\s*,\s*shape\s*=\s*(?<shape>\w+)\s*\]/
+        @static_lib_shape = $~[:shape]
+      when /\A\s*"(?<node>\w+)"\s*\[\s*label\s*=\s*"(?<label>\S+)"\s*,\s*shape\s*=\s*(?<shape>\w+)\s*\]\s*;\s*\z/
+        node = $~[:node]
+        label = $~[:label]
+        shape = $~[:shape]
+        @nodes[node] = [label, shape]
+      when /\A\s*"(?<depender>\w+)"\s*->\s*"(?<dependee>\w+)"/
+        depender = $~[:depender]
+        dependee = $~[:dependee]
+        @graph[depender] << dependee
+      end
+    end
+  end
+
+  def tsort_each_node
+    @nodes.each_key do |node|
+      yield node
+    end
+  end
+
+  def tsort_each_child(node)
+    @graph[node].each do |child|
+      yield child
+    end
+  end
+end