whispercpp 1.3.1 → 1.3.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 7f2881876a07bc3fb34dd40c70ca1cbd19688fc84f06a29dfb9abbcfd8108123
-  data.tar.gz: fae6462838866de9536a06c49ecc1b71fbaa2958862b47c42c4c0aafca363a86
+  metadata.gz: 4be24efbeaa42ad2f4c6dd82715b80d7f15fecce7529fd702eb63c20b1c33233
+  data.tar.gz: 8a588b0f1857025445b934cddf744ff91dffc1970565dba40478145978a47a65
 SHA512:
-  metadata.gz: c33d12da562d02202d576de93aebce6aa405eeb72abe961bec68745fb76ed7fc9ab7778e7f6284f13185de1e8c65c490893ad86844441f7059383e24e0624bb8
-  data.tar.gz: af9a88eb60abbfa3d77d3cfdb444dde5f07aab5a255771f348a279bce2920f34ff10a949be30ba3d77e3bb939935b0b8cca577d5cc97da83e6ece641d2fa7343
+  metadata.gz: 9ff0e5cc3e088be56975eb4c879683e223491524a384f1c5f34f79b9b772eaaaf4a233f4cecb314dea98c0121a6cf2acbfceef47afdba47f7b4cb806ceab98d8
+  data.tar.gz: 18085dafe5e4af195b806e83d670b04bab27f080ec35ff0d5d8ab4ae923541c7db17c32f2c0313d876b0ffde763fa14332a6cb01544319a76c1017a6ee49bda2

data/.gitignore

@@ -1,5 +1,6 @@
 LICENSE
 pkg/
-lib/whisper.so
-lib/whisper.bundle
-lib/whisper.dll
+lib/whisper.*
+ext/sources/*
+!ext/sources/CMakeGraphVizOptions.cmake
+ext/mkmf.log

data/README.md

@@ -16,6 +16,18 @@ 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 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 +36,15 @@ 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
@@ -60,10 +73,10 @@ You also can use shorthand for pre-converted models:
 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
@@ -87,8 +100,9 @@ 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.
@@ -97,6 +111,41 @@ 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).
+
 API
 ---
 
@@ -112,18 +161,18 @@ 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_next_turn?
+    puts line
+  end
 
 ```
 
@@ -214,18 +263,30 @@ 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.
 
 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
@@ -54,7 +73,7 @@ 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
+  chdir "tests/jfk_reader" do
     ruby "extconf.rb"
     sh "make"
   end

data/ext/.gitignore

@@ -4,10 +4,8 @@ whisper.bundle
 whisper.dll
 scripts/get-flags.mk
 *.o
-*.c
-*.cpp
-*.h
-*.m
-*.metal
-!ruby_whisper.cpp
-!ruby_whisper.h
+/*/**/*.c
+/*/**/*.cpp
+/*/**/*.h
+/*/**/*.m
+/*/**/*.metal

data/ext/dependencies.rb

@@ -0,0 +1,61 @@
+require "tsort"
+
+class Dependencies
+  def initialize(cmake, options)
+    @cmake = cmake
+    @options = options
+
+    generate_dot
+    @libs = parse_dot
+  end
+
+  def to_s
+    @libs.join(" ")
+  end
+
+  private
+
+  def dot_path
+    File.join(__dir__, "build", "whisper.cpp.dot")
+  end
+
+  def generate_dot
+    system @cmake, "-S", "sources", "-B", "build", "--graphviz", dot_path, "-D", "BUILD_SHARED_LIBS=OFF", @options.to_s, exception: true
+  end
+
+  def parse_dot
+    static_lib_shape = nil
+    nodes = {}
+    depends = Hash.new {|h, k| h[k] = []}
+
+    class << depends
+      include TSort
+      alias tsort_each_node each_key
+      def tsort_each_child(node, &block)
+        fetch(node, []).each(&block)
+      end
+    end
+
+    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]
+        depends[depender] ||= []
+        depends[depender] << dependee
+      end
+    end
+    depends.tsort.filter_map {|node|
+      label, shape = nodes[node]
+      shape == static_lib_shape ? label : nil
+    }.collect {|lib| "lib#{lib}.a"}
+      .reverse
+  end
+end

data/ext/extconf.rb

@@ -1,199 +1,22 @@
-require 'mkmf'
-
-# need to use c++ compiler flags
-$CXXFLAGS << ' -std=c++17'
-
-$LDFLAGS << ' -lstdc++'
-
-# Set to true when building binary gems
-if enable_config('static-stdlib', false)
-  $LDFLAGS << ' -static-libgcc -static-libstdc++'
-end
-
-if enable_config('march-tune-native', false)
-  $CFLAGS << ' -march=native -mtune=native'
-  $CXXFLAGS << ' -march=native -mtune=native'
-end
-
-if ENV['WHISPER_METAL']
-  $GGML_METAL ||= true
-  $DEPRECATE_WARNING ||= true
-end
-
-$UNAME_S = `uname -s`.chomp
-$UNAME_P = `uname -p`.chomp
-$UNAME_M = `uname -m`.chomp
-
-if $UNAME_S == 'Darwin'
-  unless ENV['GGML_NO_METAL']
-    $GGML_METAL ||= true
-  end
-  $GGML_NO_OPENMP ||= true
-end
-
-if $GGML_METAL
-  $GGML_METAL_EMBED_LIBRARY = true
-end
-
-$MK_CPPFLAGS = '-Iggml/include -Iggml/src -Iggml/src/ggml-cpu -Iinclude -Isrc -Iexamples'
-$MK_CFLAGS   = '-std=c11   -fPIC'
-$MK_CXXFLAGS = '-std=c++17 -fPIC'
-$MK_NVCCFLAGS = '-std=c++17'
-$MK_LDFLAGS = ''
-
-$OBJ_GGML = []
-$OBJ_WHISPER = []
-$OBJ_COMMON = []
-$OBJ_SDL = []
-
-$MK_CPPFLAGS << ' -D_XOPEN_SOURCE=600'
-
-if $UNAME_S == 'Linux'
-  $MK_CPPFLAGS << ' -D_GNU_SOURCE'
-end
-
-if $UNAME_S == 'Darwin'
-  $MK_CPPFLAGS << ' -D_DARWIN_C_SOURCE'
-end
-
-if ENV['WHISPER_DEBUG']
-  $MK_CFLAGS    << ' -O0 -g'
-  $MK_CXXFLAGS  << ' -O0 -g'
-  $MK_LDFLAGS   << ' -g'
-  $MK_NVCCFLAGS << ' -O0 -g'
-else
-  $MK_CPPFLAGS   << ' -DNDEBUG'
-  $MK_CFLAGS     << ' -O3'
-  $MK_CXXFLAGS   << ' -O3'
-  $MK_NVCCFLAGS  << ' -O3'
-end
-
-$WARN_FLAGS =
-  ' -Wall' <<
-  ' -Wextra' <<
-  ' -Wpedantic' <<
-  ' -Wcast-qual' <<
-  ' -Wno-unused-function'
-
-$MK_CFLAGS <<
-  $WARN_FLAGS <<
-  ' -Wshadow' <<
-  ' -Wstrict-prototypes' <<
-  ' -Wpointer-arith' <<
-  ' -Wmissing-prototypes' <<
-  ' -Werror=implicit-int' <<
-  ' -Werror=implicit-function-declaration'
-
-$MK_CXXFLAGS <<
-  $WARN_FLAGS <<
-  ' -Wmissing-declarations' <<
-  ' -Wmissing-noreturn'
-
-unless `#{cc_command} #{$LDFLAGS} -Wl,-v 2>&1`.chomp.include? 'dyld-1015.7'
-  $MK_CPPFLAGS << ' -DHAVE_BUGGY_APPLE_LINKER'
-end
-
-if %w[Linux Darwin FreeBSD NetBSD OpenBSD Haiku].include? $UNAME_S
-  $MK_CFLAGS   << ' -pthread'
-  $MK_CXXFLAGS << ' -pthread'
-end
-
-unless $_WIN32
-  $DSO_EXT = '.so'
-else
-  $DSO_EXT = '.dll'
-end
-
-unless ENV['RISCV']
-  if %w[x86_64 i686 amd64].include? $UNAME_M
-    $HOST_CXXFLAGS ||= ''
-
-    $MK_CFLAGS     << ' -march=native -mtune=native'
-    $HOST_CXXFLAGS << ' -march=native -mtune=native'
-  end
-else
-  $MK_CFLAGS   << ' -march=rv64gcv -mabi=lp64d'
-  $MK_CXXFLAGS << ' -march=rv64gcv -mabi=lp64d'
-end
-
-unless ENV['GGML_NO_ACCELERATE']
-  if $UNAME_S == 'Darwin'
-    $MK_CPPFLAGS << ' -DGGML_USE_ACCELERATE -DGGML_USE_BLAS -DGGML_BLAS_USE_ACCELERATE'
-    $MK_CPPFLAGS << ' -DACCELERATE_NEW_LAPACK'
-    $MK_CPPFLAGS << ' -DACCELERATE_LAPACK_ILP64'
-    $MK_LDFLAGS  << ' -framework Accelerate'
-    $OBJ_GGML    << 'ggml/src/ggml-blas/ggml-blas.o'
-  end
-end
-
-if ENV['GGML_OPENBLAS']
-  $MK_CPPFLAGS << " -DGGML_USE_BLAS #{`pkg-config --cflags-only-I openblas`.chomp}"
-  $MK_CFLAGS   << " #{`pkg-config --cflags-only-other openblas)`.chomp}"
-  $MK_LDFLAGS  << " #{`pkg-config --libs openblas`}"
-  $OBJ_GGML    << 'ggml/src/ggml-blas/ggml-blas.o'
-end
-
-if ENV['GGML_OPENBLAS64']
-  $MK_CPPFLAGS << " -DGGML_USE_BLAS #{`pkg-config --cflags-only-I openblas64`.chomp}"
-  $MK_CFLAGS   << " #{`pkg-config --cflags-only-other openblas64)`.chomp}"
-  $MK_LDFLAGS  << " #{`pkg-config --libs openblas64`}"
-  $OBJ_GGML    << 'ggml/src/ggml-blas/ggml-blas.o'
-end
-
-if $GGML_METAL
-  $MK_CPPFLAGS << ' -DGGML_USE_METAL'
-  $MK_LDFLAGS  << ' -framework Foundation -framework Metal -framework MetalKit'
-  $OBJ_GGML    << 'ggml/src/ggml-metal/ggml-metal.o'
-
-  if ENV['GGML_METAL_NDEBUG']
-    $MK_CPPFLAGS << ' -DGGML_METAL_NDEBUG'
-  end
-
-  if $GGML_METAL_EMBED_LIBRARY
-    $MK_CPPFLAGS << ' -DGGML_METAL_EMBED_LIBRARY'
-    $OBJ_GGML    << 'ggml/src/ggml-metal/ggml-metal-embed.o'
-  end
-end
-
-$OBJ_GGML <<
-  'ggml/src/ggml.o' <<
-  'ggml/src/ggml-alloc.o' <<
-  'ggml/src/ggml-backend.o' <<
-  'ggml/src/ggml-backend-reg.o' <<
-  'ggml/src/ggml-opt.o' <<
-  'ggml/src/ggml-quants.o' <<
-  'ggml/src/ggml-threading.o' <<
-  'ggml/src/ggml-cpu/ggml-cpu.o' <<
-  'ggml/src/ggml-cpu/ggml-cpu-cpp.o' <<
-  'ggml/src/ggml-cpu/ggml-cpu-aarch64.o' <<
-  'ggml/src/ggml-cpu/ggml-cpu-hbm.o' <<
-  'ggml/src/ggml-cpu/ggml-cpu-quants.o' <<
-  'ggml/src/ggml-cpu/ggml-cpu-traits.o'
-
-$OBJ_WHISPER <<
-  'src/whisper.o'
-
-$objs = $OBJ_GGML + $OBJ_WHISPER + $OBJ_COMMON + $OBJ_SDL
-$objs << "ruby_whisper.o"
-
-$CPPFLAGS  = "#{$MK_CPPFLAGS} #{$CPPFLAGS}"
-$CFLAGS    = "#{$CPPFLAGS} #{$MK_CFLAGS} #{$GF_CFLAGS} #{$CFLAGS}"
-$BASE_CXXFLAGS = "#{$MK_CXXFLAGS} #{$CXXFLAGS}"
-$CXXFLAGS  = "#{$BASE_CXXFLAGS} #{$HOST_CXXFLAGS} #{$GF_CXXFLAGS} #{$CPPFLAGS}"
-$NVCCFLAGS = "#{$MK_NVCCFLAGS} #{$NVCCFLAGS}"
-$LDFLAGS   = "#{$MK_LDFLAGS} #{$LDFLAGS}"
-
-create_makefile('whisper')
-
-File.open 'Makefile', 'a' do |file|
-  file.puts 'include scripts/get-flags.mk'
-  file.puts 'include cpu.mk'
-
-  if $GGML_METAL
-    file.puts 'include metal.mk'
-
-    if $GGML_METAL_EMBED_LIBRARY
-      file.puts 'include metal-embed.mk'
-    end
-  end
+require "mkmf"
+require_relative "options"
+require_relative "dependencies"
+
+cmake = find_executable("cmake") || abort
+options = Options.new
+have_library("gomp") rescue nil
+libs = Dependencies.new(cmake, options)
+
+$INCFLAGS << " -Isources/include -Isources/ggml/include -Isources/examples"
+$LOCAL_LIBS << " #{libs}"
+$cleanfiles << " build #{libs}"
+
+create_makefile "whisper" do |conf|
+  conf << <<~EOF
+    $(TARGET_SO): #{libs}
+    #{libs}: cmake-targets
+    cmake-targets:
+    #{"\t"}#{cmake} -S sources -B build -D BUILD_SHARED_LIBS=OFF -D CMAKE_ARCHIVE_OUTPUT_DIRECTORY=#{__dir__} -D CMAKE_POSITION_INDEPENDENT_CODE=ON #{options}
+    #{"\t"}#{cmake} --build build --config Release --target common whisper
+  EOF
 end