whispercpp 1.2.0.2 → 1.3.1

data/tests/test_segment.rb

@@ -0,0 +1,83 @@
+require_relative "helper"
+
+class TestSegment < TestBase
+  class << self
+    attr_reader :whisper
+
+    def startup
+      @whisper = Whisper::Context.new("base.en")
+      params = Whisper::Params.new
+      params.print_timestamps = false
+      @whisper.transcribe(TestBase::AUDIO, params)
+    end
+  end
+
+  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_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
+
+  private
+
+  def whisper
+    self.class.whisper
+  end
+end

data/tests/test_whisper.rb

@@ -1,138 +1,226 @@
-TOPDIR = File.expand_path(File.join(File.dirname(__FILE__), '..'))
-EXTDIR = File.join(TOPDIR, 'ext')
-#$LIBDIR = File.join(TOPDIR, 'lib')
-#$:.unshift(LIBDIR)
-$:.unshift(EXTDIR)
+require_relative "helper"
+require "stringio"
+require "etc"
 
-require 'whisper'
-require 'test/unit'
+# Exists to detect memory-related bug
+Whisper.log_set ->(level, buffer, user_data) {}, nil
 
-class TestWhisper < Test::Unit::TestCase
+class TestWhisper < TestBase
   def setup
     @params  = Whisper::Params.new
   end
 
-  def test_language
-    @params.language = "en"
-    assert_equal @params.language, "en"
-    @params.language = "auto"
-    assert_equal @params.language, "auto"
-  end
-
-  def test_offset
-    @params.offset = 10_000
-    assert_equal @params.offset, 10_000
-    @params.offset = 0
-    assert_equal @params.offset, 0
-  end
-
-  def test_duration
-    @params.duration = 60_000
-    assert_equal @params.duration, 60_000
-    @params.duration = 0
-    assert_equal @params.duration, 0
-  end
-
-  def test_max_text_tokens
-    @params.max_text_tokens = 300
-    assert_equal @params.max_text_tokens, 300
-    @params.max_text_tokens = 0
-    assert_equal @params.max_text_tokens, 0
-  end
-
-  def test_translate
-    @params.translate = true
-    assert @params.translate
-    @params.translate = false
-    assert !@params.translate
-  end
-
-  def test_no_context
-    @params.no_context = true
-    assert @params.no_context
-    @params.no_context = false
-    assert !@params.no_context
-  end
-
-  def test_single_segment
-    @params.single_segment = true
-    assert @params.single_segment
-    @params.single_segment = false
-    assert !@params.single_segment
-  end
-
-  def test_print_special
-    @params.print_special = true
-    assert @params.print_special
-    @params.print_special = false
-    assert !@params.print_special
-  end
-
-  def test_print_progress
-    @params.print_progress = true
-    assert @params.print_progress
-    @params.print_progress = false
-    assert !@params.print_progress
-  end
-
-  def test_print_realtime
-    @params.print_realtime = true
-    assert @params.print_realtime
-    @params.print_realtime = false
-    assert !@params.print_realtime
-  end
-
-  def test_print_timestamps
-    @params.print_timestamps = true
-    assert @params.print_timestamps
-    @params.print_timestamps = false
-    assert !@params.print_timestamps
-  end
-
-  def test_suppress_blank
-    @params.suppress_blank = true
-    assert @params.suppress_blank
-    @params.suppress_blank = false
-    assert !@params.suppress_blank
-  end
-
-  def test_suppress_non_speech_tokens
-    @params.suppress_non_speech_tokens = true
-    assert @params.suppress_non_speech_tokens
-    @params.suppress_non_speech_tokens = false
-    assert !@params.suppress_non_speech_tokens
-  end
-
-  def test_token_timestamps
-    @params.token_timestamps = true
-    assert @params.token_timestamps
-    @params.token_timestamps = false
-    assert !@params.token_timestamps
-  end
-
-  def test_split_on_word
-    @params.split_on_word = true
-    assert @params.split_on_word
-    @params.split_on_word = false
-    assert !@params.split_on_word
-  end
-
-  def test_speed_up
-    @params.speed_up = true
-    assert @params.speed_up
-    @params.speed_up = false
-    assert !@params.speed_up
-  end
-
   def test_whisper
-    @whisper = Whisper::Context.new(File.join(TOPDIR, '..', '..', 'models', 'ggml-base.en.bin'))
+    @whisper = Whisper::Context.new("base.en")
     params  = Whisper::Params.new
     params.print_timestamps = false
 
-    jfk = File.join(TOPDIR, '..', '..', 'samples', 'jfk.wav')
-    @whisper.transcribe(jfk, params) {|text|
+    @whisper.transcribe(AUDIO, params) {|text|
       assert_match /ask not what your country can do for you, ask what you can do for your country/, text
     }
   end
 
+  sub_test_case "After transcription" do
+    class << self
+      attr_reader :whisper
+
+      def startup
+        @whisper = Whisper::Context.new("base.en")
+        params = Whisper::Params.new
+        params.print_timestamps = false
+        @whisper.transcribe(TestBase::AUDIO, params)
+      end
+    end
+
+    def whisper
+      self.class.whisper
+    end
+
+    def test_full_n_segments
+      assert_equal 1, whisper.full_n_segments
+    end
+
+    def test_full_lang_id
+      assert_equal 0, whisper.full_lang_id
+    end
+
+    def test_full_get_segment_t0
+      assert_equal 0, whisper.full_get_segment_t0(0)
+      assert_raise IndexError do
+        whisper.full_get_segment_t0(whisper.full_n_segments)
+      end
+      assert_raise IndexError do
+        whisper.full_get_segment_t0(-1)
+      end
+    end
+
+    def test_full_get_segment_t1
+      t1 = whisper.full_get_segment_t1(0)
+      assert_kind_of Integer, t1
+      assert t1 > 0
+      assert_raise IndexError do
+        whisper.full_get_segment_t1(whisper.full_n_segments)
+      end
+    end
+
+    def test_full_get_segment_speaker_turn_next
+      assert_false whisper.full_get_segment_speaker_turn_next(0)
+    end
+
+    def test_full_get_segment_text
+      assert_match /ask not what your country can do for you, ask what you can do for your country/, whisper.full_get_segment_text(0)
+    end
+  end
+
+  def test_lang_max_id
+    assert_kind_of Integer, Whisper.lang_max_id
+  end
+
+  def test_lang_id
+    assert_equal 0, Whisper.lang_id("en")
+    assert_raise ArgumentError do
+      Whisper.lang_id("non existing language")
+    end
+  end
+
+  def test_lang_str
+    assert_equal "en", Whisper.lang_str(0)
+    assert_raise IndexError do
+      Whisper.lang_str(Whisper.lang_max_id + 1)
+    end
+  end
+
+  def test_lang_str_full
+    assert_equal "english", Whisper.lang_str_full(0)
+    assert_raise IndexError do
+      Whisper.lang_str_full(Whisper.lang_max_id + 1)
+    end
+  end
+
+  def test_log_set
+    user_data = Object.new
+    logs = []
+    log_callback = ->(level, buffer, udata) {
+      logs << [level, buffer, udata]
+    }
+    Whisper.log_set log_callback, user_data
+    Whisper::Context.new("base.en")
+
+    assert logs.length > 30
+    logs.each do |log|
+      assert_include [Whisper::LOG_LEVEL_DEBUG, Whisper::LOG_LEVEL_INFO, Whisper::LOG_LEVEL_WARN], log[0]
+      assert_same user_data, log[2]
+    end
+  end
+
+  def test_log_suppress
+    stderr = $stderr
+    Whisper.log_set ->(level, buffer, user_data) {
+      # do nothing
+    }, nil
+    dev = StringIO.new("")
+    $stderr = dev
+    Whisper::Context.new("base.en")
+    assert_empty dev.string
+  ensure
+    $stderr = stderr
+  end
+
+  sub_test_case "full" do
+    def setup
+      super
+      @whisper = Whisper::Context.new("base.en")
+      @samples = File.read(AUDIO, nil, 78).unpack("s<*").collect {|i| i.to_f / 2**15}
+    end
+
+    def test_full
+      @whisper.full(@params, @samples, @samples.length)
+
+      assert_equal 1, @whisper.full_n_segments
+      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_without_length
+      @whisper.full(@params, @samples)
+
+      assert_equal 1, @whisper.full_n_segments
+      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_enumerator
+      samples = @samples.each
+      @whisper.full(@params, samples, @samples.length)
+
+      assert_equal 1, @whisper.full_n_segments
+      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_enumerator_without_length
+      samples = @samples.each
+      assert_raise ArgumentError do
+        @whisper.full(@params, samples)
+      end
+    end
+
+    def test_full_enumerator_with_too_large_length
+      samples = @samples.each.take(10).to_enum
+      assert_raise StopIteration do
+        @whisper.full(@params, samples, 11)
+      end
+    end
+
+    def test_full_with_memory_view
+      samples = JFKReader.new(AUDIO)
+      @whisper.full(@params, samples)
+
+      assert_equal 1, @whisper.full_n_segments
+      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_parallel
+      @whisper.full_parallel(@params, @samples, @samples.length, Etc.nprocessors)
+
+      assert_equal Etc.nprocessors, @whisper.full_n_segments
+      text = @whisper.each_segment.collect(&:text).join
+      assert_match /ask what you can do/i, text
+      assert_match /for your country/i, text
+    end
+
+    def test_full_parallel_with_memory_view
+      samples = JFKReader.new(AUDIO)
+      @whisper.full_parallel(@params, samples, nil, Etc.nprocessors)
+
+      assert_equal Etc.nprocessors, @whisper.full_n_segments
+      text = @whisper.each_segment.collect(&:text).join
+      assert_match /ask what you can do/i, text
+      assert_match /for your country/i, text
+    end
+
+    def test_full_parallel_without_length_and_n_processors
+      @whisper.full_parallel(@params, @samples)
+
+      assert_equal 1, @whisper.full_n_segments
+      text = @whisper.each_segment.collect(&:text).join
+      assert_match /ask what you can do/i, text
+      assert_match /for your country/i, text
+    end
+
+    def test_full_parallel_without_length
+      @whisper.full_parallel(@params, @samples, nil, Etc.nprocessors)
+
+      assert_equal Etc.nprocessors, @whisper.full_n_segments
+      text = @whisper.each_segment.collect(&:text).join
+      assert_match /ask what you can do/i, text
+      assert_match /for your country/i, text
+    end
+
+    def test_full_parallel_without_n_processors
+      @whisper.full_parallel(@params, @samples, @samples.length)
+
+      assert_equal 1, @whisper.full_n_segments
+      text = @whisper.each_segment.collect(&:text).join
+      assert_match /ask what you can do/i, text
+      assert_match /for your country/i, text
+    end
+  end
 end

data/whispercpp.gemspec

@@ -0,0 +1,36 @@
+require_relative "extsources"
+
+Gem::Specification.new do |s|
+  s.name    = "whispercpp"
+  s.authors = ["Georgi Gerganov", "Todd A. Fisher"]
+  s.version = '1.3.1'
+  s.date    = '2024-12-19'
+  s.description = %q{High-performance inference of OpenAI's Whisper automatic speech recognition (ASR) model via Ruby}
+  s.email   = 'todd.fisher@gmail.com'
+  s.extra_rdoc_files = ['LICENSE', 'README.md']
+
+  s.files = `git ls-files . -z`.split("\x0") +
+              EXTSOURCES.collect {|file|
+                basename = File.basename(file)
+                if s.extra_rdoc_files.include?(basename)
+                  basename
+                else
+                  file.sub("../..", "ext")
+                end
+              }
+
+  s.summary = %q{Ruby whisper.cpp bindings}
+  s.test_files = s.files.select {|file| file.start_with? "tests/"}
+
+  s.extensions << 'ext/extconf.rb'
+  s.required_ruby_version = '>= 3.1.0'
+
+  #### Documentation and testing.
+  s.homepage = 'https://github.com/ggerganov/whisper.cpp'
+  s.rdoc_options = ['--main', 'README.md']
+
+
+    s.platform = Gem::Platform::RUBY
+
+  s.licenses = ['MIT']
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: whispercpp
 version: !ruby/object:Gem::Version
-  version: 1.2.0.2
+  version: 1.3.1
 platform: ruby
 authors:
 - Georgi Gerganov
@@ -9,7 +9,7 @@ authors:
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2023-02-27 00:00:00.000000000 Z
+date: 2024-12-19 00:00:00.000000000 Z
 dependencies: []
 description: High-performance inference of OpenAI's Whisper automatic speech recognition
   (ASR) model via Ruby
@@ -21,18 +21,135 @@ extra_rdoc_files:
 - LICENSE
 - README.md
 files:
+- ".gitignore"
 - LICENSE
 - README.md
 - Rakefile
-- ext/dr_wav.h
+- ext/.gitignore
+- ext/cpu.mk
+- ext/examples/dr_wav.h
 - ext/extconf.rb
-- ext/ggml.c
-- ext/ggml.h
+- ext/ggml/include/ggml-alloc.h
+- ext/ggml/include/ggml-backend.h
+- ext/ggml/include/ggml-blas.h
+- ext/ggml/include/ggml-cann.h
+- ext/ggml/include/ggml-cpp.h
+- ext/ggml/include/ggml-cpu.h
+- ext/ggml/include/ggml-cuda.h
+- ext/ggml/include/ggml-kompute.h
+- ext/ggml/include/ggml-metal.h
+- ext/ggml/include/ggml-opencl.h
+- ext/ggml/include/ggml-opt.h
+- ext/ggml/include/ggml-rpc.h
+- ext/ggml/include/ggml-sycl.h
+- ext/ggml/include/ggml-vulkan.h
+- ext/ggml/include/ggml.h
+- ext/ggml/src/ggml-alloc.c
+- ext/ggml/src/ggml-amx/common.h
+- ext/ggml/src/ggml-amx/ggml-amx.cpp
+- ext/ggml/src/ggml-amx/mmq.cpp
+- ext/ggml/src/ggml-amx/mmq.h
+- ext/ggml/src/ggml-backend-impl.h
+- ext/ggml/src/ggml-backend-reg.cpp
+- ext/ggml/src/ggml-backend.cpp
+- ext/ggml/src/ggml-blas/ggml-blas.cpp
+- ext/ggml/src/ggml-cann/acl_tensor.cpp
+- ext/ggml/src/ggml-cann/acl_tensor.h
+- ext/ggml/src/ggml-cann/aclnn_ops.cpp
+- ext/ggml/src/ggml-cann/aclnn_ops.h
+- ext/ggml/src/ggml-cann/common.h
+- ext/ggml/src/ggml-cann/ggml-cann.cpp
+- ext/ggml/src/ggml-cann/kernels/ascendc_kernels.h
+- ext/ggml/src/ggml-cann/kernels/dup.cpp
+- ext/ggml/src/ggml-cann/kernels/get_row_f16.cpp
+- ext/ggml/src/ggml-cann/kernels/get_row_f32.cpp
+- ext/ggml/src/ggml-cann/kernels/get_row_q4_0.cpp
+- ext/ggml/src/ggml-cann/kernels/get_row_q8_0.cpp
+- ext/ggml/src/ggml-cann/kernels/quantize_f16_q8_0.cpp
+- ext/ggml/src/ggml-cann/kernels/quantize_f32_q8_0.cpp
+- ext/ggml/src/ggml-cann/kernels/quantize_float_to_q4_0.cpp
+- ext/ggml/src/ggml-common.h
+- ext/ggml/src/ggml-cpu/amx/amx.cpp
+- ext/ggml/src/ggml-cpu/amx/amx.h
+- ext/ggml/src/ggml-cpu/amx/common.h
+- ext/ggml/src/ggml-cpu/amx/mmq.cpp
+- ext/ggml/src/ggml-cpu/amx/mmq.h
+- ext/ggml/src/ggml-cpu/cpu-feats-x86.cpp
+- ext/ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp
+- ext/ggml/src/ggml-cpu/ggml-cpu-aarch64.h
+- ext/ggml/src/ggml-cpu/ggml-cpu-hbm.cpp
+- ext/ggml/src/ggml-cpu/ggml-cpu-hbm.h
+- ext/ggml/src/ggml-cpu/ggml-cpu-impl.h
+- ext/ggml/src/ggml-cpu/ggml-cpu-quants.c
+- ext/ggml/src/ggml-cpu/ggml-cpu-quants.h
+- ext/ggml/src/ggml-cpu/ggml-cpu-traits.cpp
+- ext/ggml/src/ggml-cpu/ggml-cpu-traits.h
+- ext/ggml/src/ggml-cpu/ggml-cpu.c
+- ext/ggml/src/ggml-cpu/ggml-cpu.cpp
+- ext/ggml/src/ggml-cpu/llamafile/sgemm.cpp
+- ext/ggml/src/ggml-cpu/llamafile/sgemm.h
+- ext/ggml/src/ggml-cuda/vendors/cuda.h
+- ext/ggml/src/ggml-cuda/vendors/hip.h
+- ext/ggml/src/ggml-cuda/vendors/musa.h
+- ext/ggml/src/ggml-impl.h
+- ext/ggml/src/ggml-kompute/ggml-kompute.cpp
+- ext/ggml/src/ggml-metal/ggml-metal-impl.h
+- ext/ggml/src/ggml-metal/ggml-metal.m
+- ext/ggml/src/ggml-metal/ggml-metal.metal
+- ext/ggml/src/ggml-opt.cpp
+- ext/ggml/src/ggml-quants.c
+- ext/ggml/src/ggml-quants.h
+- ext/ggml/src/ggml-rpc/ggml-rpc.cpp
+- ext/ggml/src/ggml-sycl/common.cpp
+- ext/ggml/src/ggml-sycl/concat.cpp
+- ext/ggml/src/ggml-sycl/conv.cpp
+- ext/ggml/src/ggml-sycl/convert.cpp
+- ext/ggml/src/ggml-sycl/dmmv.cpp
+- ext/ggml/src/ggml-sycl/element_wise.cpp
+- ext/ggml/src/ggml-sycl/ggml-sycl.cpp
+- ext/ggml/src/ggml-sycl/im2col.cpp
+- ext/ggml/src/ggml-sycl/mmq.cpp
+- ext/ggml/src/ggml-sycl/mmvq.cpp
+- ext/ggml/src/ggml-sycl/norm.cpp
+- ext/ggml/src/ggml-sycl/outprod.cpp
+- ext/ggml/src/ggml-sycl/rope.cpp
+- ext/ggml/src/ggml-sycl/softmax.cpp
+- ext/ggml/src/ggml-sycl/tsembd.cpp
+- ext/ggml/src/ggml-sycl/wkv6.cpp
+- ext/ggml/src/ggml-threading.cpp
+- ext/ggml/src/ggml-threading.h
+- ext/ggml/src/ggml-vulkan/ggml-vulkan.cpp
+- ext/ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp
+- ext/ggml/src/ggml.c
+- ext/include/whisper.h
+- ext/metal-embed.mk
+- ext/metal.mk
 - ext/ruby_whisper.cpp
 - ext/ruby_whisper.h
-- ext/whisper.cpp
-- ext/whisper.h
+- ext/scripts/get-flags.mk
+- ext/src/coreml/whisper-decoder-impl.h
+- ext/src/coreml/whisper-decoder-impl.m
+- ext/src/coreml/whisper-encoder-impl.h
+- ext/src/coreml/whisper-encoder-impl.m
+- ext/src/coreml/whisper-encoder.h
+- ext/src/openvino/whisper-openvino-encoder.cpp
+- ext/src/openvino/whisper-openvino-encoder.h
+- ext/src/whisper.cpp
+- extsources.rb
+- lib/whisper.rb
+- lib/whisper/model/uri.rb
+- tests/helper.rb
+- tests/jfk_reader/.gitignore
+- tests/jfk_reader/extconf.rb
+- tests/jfk_reader/jfk_reader.c
+- tests/test_callback.rb
+- tests/test_error.rb
+- tests/test_model.rb
+- tests/test_package.rb
+- tests/test_params.rb
+- tests/test_segment.rb
 - tests/test_whisper.rb
+- whispercpp.gemspec
 homepage: https://github.com/ggerganov/whisper.cpp
 licenses:
 - MIT
@@ -40,24 +157,33 @@ metadata: {}
 post_install_message:
 rdoc_options:
 - "--main"
-- "../../README.md"
+- README.md
 require_paths:
 - lib
-- ext
 required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '0'
+      version: 3.1.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.2.33
+rubygems_version: 3.5.22
 signing_key:
 specification_version: 4
 summary: Ruby whisper.cpp bindings
 test_files:
+- tests/helper.rb
+- tests/jfk_reader/.gitignore
+- tests/jfk_reader/extconf.rb
+- tests/jfk_reader/jfk_reader.c
+- tests/test_callback.rb
+- tests/test_error.rb
+- tests/test_model.rb
+- tests/test_package.rb
+- tests/test_params.rb
+- tests/test_segment.rb
 - tests/test_whisper.rb