gtcrn 0.0.1 → 0.0.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (6) hide show
  1. checksums.yaml +4 -4
  2. data/README.md +2 -2
  3. data/bin/gtcrn +18 -1
  4. data/gtcrn.gemspec +1 -1
  5. data/lib/gtcrn.rb +2 -2
  6. metadata +1 -1
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA256:
3
- metadata.gz: 684bab48a155c6ad43d42479fd8c361632a4c51d1ecf19f388e7487e575c3ce4
4
- data.tar.gz: 78655c56cf93b6839ba193112534c02a4e8d73084c89ec6536dc9db6cfb12032
3
+ metadata.gz: e62dd7f2ba7da50ab841769e0ccc9d0aeef8f0a31499a2a59b80ffc749b1ca9b
4
+ data.tar.gz: 555a5c91d412822e1e066bb1ea4bccdfd1cdf9e334adad025b886aea3a2b62f3
5
5
  SHA512:
6
- metadata.gz: e71548aba12e685361ab24a6f2a1574a151cce46c622bf281f54254273b9f8e83ad7ced377ff0ad0b9096e530fef2c1dab289f6a3f1bd3457d511599960ecc64
7
- data.tar.gz: a8ad7d5e076c0257a79a7952fc96ab15f001280113cbc05f7e0d49d6b4ddb95ae562a02ffc15e25d94b4b8b84a6390eaaae434cd5899b91fd0622af1a2e1f43f
6
+ metadata.gz: c82eb21211da591054d65de5aa131219432f20ce161b53b750d961baed6bd5e3f840076ff17dcdf9568a059257544de648a33c1f7d51911e0513c2e855bb3e2e
7
+ data.tar.gz: 50814826a17fb42e874f7ea7bd8fae2366f4b08d2961c2e354f4b8b9e4346199d37e61495c4a236cafc46f9886c2a1a9ba6f4b4e9b1b5f5e6f837a0a16265f03
data/README.md CHANGED
@@ -16,14 +16,14 @@ output = GTCRN.new.enhance_speech("path/to/audio.wav")
16
16
  # => <Pathname:path/to/audio.enhanced.wav>
17
17
  ````
18
18
 
19
- Audio file must be monoral WAV with 16kHz sampling rate and 16-bit per sample..
19
+ Audio file must be mono WAV with 16kHz sampling rate and 16-bit per sample.
20
20
 
21
21
  CLI
22
22
  ---
23
23
 
24
24
  This gem ships with `gtcrn` command.
25
25
 
26
- % gtcrn path/to/audio.wav path/to/output.wav
26
+ % gtcrn path/to/audio.wav --output=path/to/output.wav
27
27
  Enhanced file written to
28
28
  path/to/output.wav
29
29
 
data/bin/gtcrn CHANGED
@@ -1,11 +1,28 @@
1
+ require "optparse"
1
2
  require "gtcrn"
2
3
 
3
4
  def main(argv)
5
+ options = parse_options(argv)
4
6
  input = argv.shift
5
7
  abort "Specify input file" unless input
6
- output = GTCRN.new.enhance_speech(input, argv.shift)
8
+ output = GTCRN.new.enhance_speech(input, options[:output])
7
9
  $stderr.puts "Enhanced file written to"
8
10
  $stderr.puts output
9
11
  end
10
12
 
13
+ def parse_options(argv)
14
+ options = {}
15
+ OptionParser.new {|opt|
16
+ opt.banner = <<~EOB
17
+ Enhance speech properties of GTCRN files
18
+
19
+ Usage: gtcrn [options] INPUT
20
+ EOB
21
+ opt.on "-o", "--output=PATH", "Specify output file or directory" do |path|
22
+ options[:output] = path
23
+ end
24
+ }.parse!(argv)
25
+ options
26
+ end
27
+
11
28
  main ARGV
data/gtcrn.gemspec CHANGED
@@ -1,6 +1,6 @@
1
1
  Gem::Specification.new do |s|
2
2
  s.name = "gtcrn"
3
- s.version = "0.0.1"
3
+ s.version = "0.0.2"
4
4
  s.authors = ["Kitaiti Makoto"]
5
5
  s.email = ["KitaitiMakoto@gmail.com"]
6
6
  s.summary = "Denoises audio"
data/lib/gtcrn.rb CHANGED
@@ -35,7 +35,7 @@ class GTCRN
35
35
  waveform, sample_rate = TorchAudio.load(path.to_path)
36
36
  raise "Sampling rate must be 16000 Hz, but given: #{sample_rate} Hz" unless sample_rate == 16000
37
37
  enhanced = enhance_speech_waveform(waveform)
38
- TorchAudio.save(dest.to_path, enhanced.squeeze, sample_rate)
38
+ TorchAudio.save(dest.to_path, enhanced, sample_rate)
39
39
 
40
40
  dest
41
41
  end
@@ -66,6 +66,6 @@ class GTCRN
66
66
  Torch.from_numo(real) + 1i * Torch.from_numo(imag),
67
67
  **ISTFT_OPTS
68
68
  )
69
- enhanced
69
+ enhanced.squeeze
70
70
  end
71
71
  end
metadata CHANGED
@@ -1,7 +1,7 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: gtcrn
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.0.1
4
+ version: 0.0.2
5
5
  platform: ruby
6
6
  authors:
7
7
  - Kitaiti Makoto