itak 1 → 3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 1571ecc53ee18992338a73e4277e067576e8297ef871e9a748953ef34c8843c8
-  data.tar.gz: 54a21a999995f4bf6db51023df49b2590df4a8296f8ceda7b0b012303cbd950a
+  metadata.gz: a7ab66466c640ba4b91cfdf41de938434bdf3decd225c606213ff0aa91a9cff2
+  data.tar.gz: 8eabbd49439e13cd6d1831a7fc5fd83a391538f89a06e9c69640ba3ec5006ace
 SHA512:
-  metadata.gz: 5ce6ae6455378ce71b46ecc4e57e32fb2c70b018183cb615333cd303bf998dba6b5711a723a7b0381cb974ac2e297042036c653756fac7ef7b2cc76f3471d3a0
-  data.tar.gz: 6cd9714589ff2ad220b718020237b107c618e0e4d78f34e0f5e42f0ef8ff1970d17250d0cef7505be68416c5cf49fddb1ddc08e14dd76f45c8e1dff7cdfa5b4b
+  metadata.gz: 0f7278553178a3d2fa2de089f14a71f5079814528772adccd5fd1897056b31fb5a624efe5b73c2a8779f6d3bb7e8ee213cea8aea8fc26a1f9984967b9b6a75c7
+  data.tar.gz: ed4f9e3765197050aa8061e52cad8cfcbed747f00c2433e59f80fa7ce1a715255be4ec0e36ecc7d78cae85dc7fc8463d4aa2fc7154eee3e12eda0b882b7d069c

data/README.md

@@ -3,7 +3,12 @@ Itak
 
 Audio editing tool for podcasters.
 
-It denoises and removes non-active period from the audio file.
+It does:
+
+* remove noise, and
+* remove non-active period
+
+from the audio file.
 
 SYNOPSIS
 --------

data/bin/itak

@@ -1,4 +1,5 @@
 require "optparse"
+require "optparse/pathname"
 require "itak"
 
 def main(argv)
@@ -8,6 +9,8 @@ def main(argv)
   output = Itak.new.run(src, options[:output])
   $stderr.puts "Output written to"
   $stderr.puts output
+rescue => err
+  abort err.message
 end
 
 def parse_options(argv)
@@ -18,7 +21,7 @@ def parse_options(argv)
 
       Usage: itak [options] INPUT
     EOB
-    opt.on "-o", "--output=PATH", "Specify output file or directory" do |path|
+    opt.on "-o", "--output=PATH", "Specify output file or directory", Pathname do |path|
       options[:output] = path
     end
   }.parse!(argv)

data/itak.gemspec

@@ -1,6 +1,6 @@
 Gem::Specification.new do |s|
   s.name = "itak"
-  s.version = "1"
+  s.version = "3"
   s.authors = ["Kitaiti Makoto"]
   s.email = ["KitaitiMaokto@gmail.com"]
   s.summary = "Audio editing tool for podcasters"
@@ -11,9 +11,13 @@ Gem::Specification.new do |s|
   s.files = `git ls-files -z`.split("\x0")
   s.executables = s.files.filter_map {|f| File.basename(f) if f.start_with?("bin/")}
 
-  s.add_runtime_dependency "gtcrn"
-  s.add_runtime_dependency "whispercpp"
-  s.add_runtime_dependency "torchaudio"
+  s.add_runtime_dependency "gtcrn", ">= 0.0.2"
+  s.add_runtime_dependency "whispercpp", ">= 1.3.6"
+  s.add_runtime_dependency "torchaudio", ">= 0.5.0"
+  s.add_runtime_dependency "torchcodec"
+  s.add_runtime_dependency "torch-rb"
+  s.add_runtime_dependency "optparse-pathname"
+  s.add_runtime_dependency "ndav-torch-tensor"
 
   s.add_development_dependency "rake"
   s.add_development_dependency "rubygems-tasks"

data/lib/itak/denoiser.rb

@@ -1,16 +1,13 @@
-require "fileutils"
 require "gtcrn"
 
 class Itak
   class Denoiser
-    def initialize(work_dir: nil)
-      @work_dir = work_dir ? Pathname(work_dir) : nil
+    def initialize
+      @gtcrn = GTCRN.new
     end
 
-    def denoise(src, dest: nil)
-      dir = @work_dir || Pathname.mktmpdir
-      dest ||= dir/src.sub_ext(".denoised" + src.extname).basename
-      GTCRN.new.enhance_speech(src, dest)
+    def denoise(src)
+      @gtcrn.enhance_speech_waveform(src)
     end
   end
 end

data/lib/itak/transcriber.rb

@@ -0,0 +1,39 @@
+require "whisper"
+
+class Itak
+  class Transcriber
+    PARAMS = {
+      language: "ja",
+      temperature: 1.0
+    }
+
+    def initialize(model: "large-v3-turbo-q8_0")
+      Whisper.log_set proc {}, nil
+      @whisper = Whisper::Context.new(model)
+    end
+
+    def run(src, params: {})
+      params = Whisper::Params.new(**PARAMS.merge(params))
+      src = src[0] if src.ndim == 2 && src.shape[0] == 1
+      @whisper
+        .full(params, src.to_ndav)
+        .each_segment
+        .collect {|segment|
+          "[%<start_time>s --> %<end_time>s]%<text>s" % {
+            start_time: format_time(segment.start_time),
+            end_time: format_time(segment.end_time),
+            text: segment.text
+          }
+        }.join("\n\n")
+    end
+
+    private
+
+    def format_time(time_ms)
+      sec, decimal_part = time_ms.divmod(1000)
+      min, sec = sec.divmod(60)
+      hour, min = min.divmod(60)
+      "%02d:%02d:%02d" % [hour, min, sec]
+    end
+  end
+end

data/lib/itak/vad.rb

@@ -1,33 +1,28 @@
-require "pathname"
-require "fileutils"
 require "whisper"
-require "torchaudio"
+require "ndav/torch/tensor"
 
 class Itak
   class VAD
+    PARAMS = Whisper::VAD::Params.new(
+      threshold: 0.7,
+      min_silence_duration_ms: 1500
+    )
+
     def initialize(model: "silero-v6.2.0")
-      @model = model
+      Whisper.log_set proc {}, nil
+      @vad = Whisper::VAD::Context.new(model)
     end
 
-    def run(src, dest, params: nil)
-      src = Pathname(src)
-      dest = Pathname(dest)
-      context = Whisper::VAD::Context.new(@model)
-      params ||= Whisper::VAD::Params.new(
-        threshold: 0.7,
-        min_silence_duration_ms: 1000
-      )
-      waveform, sample_rate = TorchAudio.load(src)
+    def run(src, params: PARAMS)
+      src = src[0] if src.ndim == 2 && src.shape[0] == 1
       chunks = []
-      context.detect(src.to_path, params).each do |segment|
+      @vad.segments_from_samples(params, src.to_ndav).each do |segment|
         segment => {start_time:, end_time:}
-        st = start_time * sample_rate / 1000
-        en = end_time * sample_rate / 1000
-        chunks << waveform[0][st..en]
+        st = start_time * SAMPLE_RATE / 1000
+        en = end_time * SAMPLE_RATE / 1000
+        chunks << src[st..en]
       end
-      output = Torch.cat(chunks)
-      TorchAudio.save(dest.to_path, output.unsqueeze(0), sample_rate)
-      dest
+      Torch.cat(chunks)
     end
   end
 end

data/lib/itak.rb

@@ -1,10 +1,13 @@
 require "pathname"
-require "tmpdir"
+require "torchaudio"
 
 require "itak/denoiser"
 require "itak/vad"
+require "itak/transcriber"
 
 class Itak
+  SAMPLE_RATE = 16_000
+
   def run(src, dest=nil)
     src = Pathname(src)
     if dest
@@ -15,13 +18,30 @@ class Itak
     else
       dest = src.sub_ext(".denoised-vad" + src.extname)
     end
+    dest.dirname.mkpath
 
-    Pathname.mktmpdir do |work_dir|
-      # TODO: Use memory instead of files to pipeline data
-      denoised = Denoiser.new(work_dir:).denoise(src)
-      VAD.new.run(denoised, dest)
-    end
+    waveform, sample_rate = TorchAudio.load(src.to_path)
+    raise "Currently only #{SAMPLE_RATE}Hz audio is supported" unless sample_rate == SAMPLE_RATE
+
+    $stderr.puts "Denoising..."
+    denoised = Denoiser.new.denoise(waveform)
+
+    $stderr.puts "VAD..."
+    vadded = VAD.new.run(denoised)
 
+    saving = Thread.new {
+      TorchAudio.save(dest.to_path, vadded.unsqueeze(0), SAMPLE_RATE)
+      $stderr.puts "Saved to #{dest}"
+    }
+    transcribing = Thread.new {
+      $stderr.puts "Transcribing..."
+      transcription = Transcriber.new.run(vadded)
+      transcription_path = dest.sub_ext(".txt")
+      transcription_path.write transcription
+      $stderr.puts "Transcription saved to #{transcription_path}"
+    }
+    saving.join
+    transcribing.join
     dest
   end
 end

data/test/test_itak.rb

@@ -9,6 +9,7 @@ class TestItak < TestBase
     output = Itak.new.run(@src)
     assert_equal Pathname("test/fixtures/mix.denoised-vad.wav").expand_path, output
     assert_path_exist output
+    assert_path_exist output.sub_ext(".txt")
 
     src_reader = WaveFile::Reader.new(@src)
     src_reader.close

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: itak
 version: !ruby/object:Gem::Version
-  version: '1'
+  version: '3'
 platform: ruby
 authors:
 - Kitaiti Makoto
@@ -11,6 +11,48 @@ date: 1980-01-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: gtcrn
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.0.2
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.0.2
+- !ruby/object:Gem::Dependency
+  name: whispercpp
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.3.6
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.3.6
+- !ruby/object:Gem::Dependency
+  name: torchaudio
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.5.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.5.0
+- !ruby/object:Gem::Dependency
+  name: torchcodec
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -24,7 +66,7 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: whispercpp
+  name: torch-rb
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -38,7 +80,21 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: torchaudio
+  name: optparse-pathname
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: ndav-torch-tensor
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -167,6 +223,7 @@ files:
 - itak.gemspec
 - lib/itak.rb
 - lib/itak/denoiser.rb
+- lib/itak/transcriber.rb
 - lib/itak/vad.rb
 - test/fixtures/.gitkeep
 - test/helper.rb
@@ -189,7 +246,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 4.0.3
+rubygems_version: 4.0.6
 specification_version: 4
 summary: Audio editing tool for podcasters
 test_files: []