speech2text 0.0.3 → 0.01
Sign up to get free protection for your applications and to get access to all the features.
- data/README.rdoc +4 -11
- data/bin/speech2text +0 -5
- data/lib/speech.rb +0 -1
- data/lib/speech/audio_inspector.rb +0 -1
- data/lib/speech/audio_splitter.rb +1 -2
- data/lib/speech/audio_to_text.rb +0 -6
- data/lib/speech/text.rb +11 -0
- data/lib/speech/version.rb +1 -2
- data/speech2text.gemspec +8 -9
- data/test/audio_inspector_test.rb +0 -1
- data/test/audio_splitter_test.rb +1 -2
- data/test/i-like-pickles.wav +0 -0
- metadata +9 -10
- data/test/audio_to_text_test.rb +0 -21
- data/test/samples/i-like-pickles.json +0 -1
data/README.rdoc
CHANGED
@@ -2,16 +2,9 @@
|
|
2
2
|
|
3
3
|
Using the power of ffmpeg/flac/Google and ruby here is a simple interface to play with to convert speech to text.
|
4
4
|
|
5
|
-
|
5
|
+
At this point the API from Google is not documented and seemly free.
|
6
|
+
The Google API will frequently return 500 errors without providing much reason as to why.
|
6
7
|
|
7
|
-
|
8
|
+
It's possible that Google will decide to not open this API up and this effort my completely be for not...
|
8
9
|
|
9
|
-
|
10
|
-
|
11
|
-
It also appears that the API only likes smaller audio files so there is a built in chunker that allows us to split the audio up into smaller chunks.
|
12
|
-
|
13
|
-
== Example
|
14
|
-
|
15
|
-
audio = Speech::AudioToText.new("i-like-pickles.wav")
|
16
|
-
puts audio.to_text.inspect
|
17
|
-
=> {"captured_json"=>[["I like pickles", 0.92731786]], "confidence"=>0.92731786}
|
10
|
+
This was all made possible in short order all thanks to Chrome 11 and http://mikepultz.com/2011/03/accessing-google-speech-api-chrome-11/
|
data/bin/speech2text
CHANGED
data/lib/speech.rb
CHANGED
@@ -1,4 +1,3 @@
|
|
1
|
-
# -*- encoding: binary -*-
|
2
1
|
module Speech
|
3
2
|
|
4
3
|
class AudioSplitter
|
@@ -9,7 +8,7 @@ module Speech
|
|
9
8
|
|
10
9
|
def initialize(splitter, offset, duration)
|
11
10
|
self.offset = offset
|
12
|
-
self.chunk =
|
11
|
+
self.chunk = "chunk-" + splitter.original_file.gsub(/\.(.*)$/, "-#{offset}" + '.\1')
|
13
12
|
self.duration = duration
|
14
13
|
self.splitter = splitter
|
15
14
|
end
|
data/lib/speech/audio_to_text.rb
CHANGED
@@ -1,4 +1,3 @@
|
|
1
|
-
# -*- encoding: binary -*-
|
2
1
|
module Speech
|
3
2
|
|
4
3
|
class AudioToText
|
@@ -22,10 +21,6 @@ module Speech
|
|
22
21
|
JSON.parse(File.read(self.captured_file))
|
23
22
|
end
|
24
23
|
|
25
|
-
def clean
|
26
|
-
File.unlink self.captured_file if self.captured_file && File.exist?(self.captured_file)
|
27
|
-
end
|
28
|
-
|
29
24
|
protected
|
30
25
|
|
31
26
|
def convert_chunk(easy, chunk, options={})
|
@@ -34,7 +29,6 @@ module Speech
|
|
34
29
|
while retrying
|
35
30
|
#easy.verbose = true
|
36
31
|
easy.headers['Content-Type'] = "audio/x-flac; rate=#{chunk.flac_rate}"
|
37
|
-
easy.headers['User-Agent'] = "https://github.com/taf2/speech2text"
|
38
32
|
easy.post_body = "Content=#{chunk.to_flac_bytes}"
|
39
33
|
easy.on_progress {|dl_total, dl_now, ul_total, ul_now| printf("%.2f/%.2f\r", ul_now, ul_total); true }
|
40
34
|
easy.on_complete {|easy| puts }
|
data/lib/speech/text.rb
ADDED
data/lib/speech/version.rb
CHANGED
data/speech2text.gemspec
CHANGED
@@ -2,15 +2,14 @@ $:.unshift File.expand_path(File.dirname(__FILE__) + "/lib")
|
|
2
2
|
require "speech/version"
|
3
3
|
|
4
4
|
Gem::Specification.new do |s|
|
5
|
-
s.name
|
6
|
-
s.authors
|
7
|
-
s.email
|
8
|
-
s.version
|
9
|
-
s.homepage
|
10
|
-
s.summary
|
11
|
-
s.description
|
12
|
-
s.files
|
13
|
-
s.executables = %w(speech2text)
|
5
|
+
s.name = "speech2text"
|
6
|
+
s.authors = ["Todd A. Fisher"]
|
7
|
+
s.email = "todd.fisher@gmail.com"
|
8
|
+
s.version = Speech::Info::VERSION
|
9
|
+
s.homepage = "https://github.com/taf2/speech2text"
|
10
|
+
s.summary = "Speech to Text Library"
|
11
|
+
s.description = "Super powers of Google wrapped in a nice Ruby interface"
|
12
|
+
s.files = Dir["{lib,bin,test}/**/*", "Rakefile", "README.rdoc", "*.gemspec"]
|
14
13
|
|
15
14
|
s.add_dependency "curb"
|
16
15
|
s.add_dependency "json"
|
data/test/audio_splitter_test.rb
CHANGED
@@ -1,4 +1,3 @@
|
|
1
|
-
# -*- encoding: binary -*-
|
2
1
|
require 'test/unit'
|
3
2
|
$:.unshift File.expand_path(File.dirname(__FILE__) + '/../lib')
|
4
3
|
require 'speech'
|
@@ -6,7 +5,7 @@ require 'speech'
|
|
6
5
|
class SpeechAudioSplitterTest < Test::Unit::TestCase
|
7
6
|
|
8
7
|
def test_audio_splitter
|
9
|
-
splitter = Speech::AudioSplitter.new("
|
8
|
+
splitter = Speech::AudioSplitter.new("i-like-pickles.wav", 1)
|
10
9
|
|
11
10
|
assert_equal '00:00:03:52', splitter.duration.to_s
|
12
11
|
assert_equal 3.52, splitter.duration.to_f
|
Binary file
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: speech2text
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: '0.01'
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -9,12 +9,12 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2011-03-
|
12
|
+
date: 2011-03-24 00:00:00.000000000 -04:00
|
13
13
|
default_executable:
|
14
14
|
dependencies:
|
15
15
|
- !ruby/object:Gem::Dependency
|
16
16
|
name: curb
|
17
|
-
requirement: &
|
17
|
+
requirement: &2157005460 !ruby/object:Gem::Requirement
|
18
18
|
none: false
|
19
19
|
requirements:
|
20
20
|
- - ! '>='
|
@@ -22,10 +22,10 @@ dependencies:
|
|
22
22
|
version: '0'
|
23
23
|
type: :runtime
|
24
24
|
prerelease: false
|
25
|
-
version_requirements: *
|
25
|
+
version_requirements: *2157005460
|
26
26
|
- !ruby/object:Gem::Dependency
|
27
27
|
name: json
|
28
|
-
requirement: &
|
28
|
+
requirement: &2157005040 !ruby/object:Gem::Requirement
|
29
29
|
none: false
|
30
30
|
requirements:
|
31
31
|
- - ! '>='
|
@@ -33,25 +33,24 @@ dependencies:
|
|
33
33
|
version: '0'
|
34
34
|
type: :runtime
|
35
35
|
prerelease: false
|
36
|
-
version_requirements: *
|
36
|
+
version_requirements: *2157005040
|
37
37
|
description: Super powers of Google wrapped in a nice Ruby interface
|
38
38
|
email: todd.fisher@gmail.com
|
39
|
-
executables:
|
40
|
-
- speech2text
|
39
|
+
executables: []
|
41
40
|
extensions: []
|
42
41
|
extra_rdoc_files: []
|
43
42
|
files:
|
44
43
|
- lib/speech/audio_inspector.rb
|
45
44
|
- lib/speech/audio_splitter.rb
|
46
45
|
- lib/speech/audio_to_text.rb
|
46
|
+
- lib/speech/text.rb
|
47
47
|
- lib/speech/version.rb
|
48
48
|
- lib/speech.rb
|
49
49
|
- bin/speech2text
|
50
50
|
- test/audio_inspector_test.rb
|
51
51
|
- test/audio_splitter_test.rb
|
52
|
-
- test/
|
52
|
+
- test/i-like-pickles.wav
|
53
53
|
- test/SampleAudio.wav
|
54
|
-
- test/samples/i-like-pickles.json
|
55
54
|
- test/samples/i-like-pickles.wav
|
56
55
|
- Rakefile
|
57
56
|
- README.rdoc
|
data/test/audio_to_text_test.rb
DELETED
@@ -1,21 +0,0 @@
|
|
1
|
-
# -*- encoding: binary -*-
|
2
|
-
require 'test/unit'
|
3
|
-
$:.unshift File.expand_path(File.dirname(__FILE__) + '/../lib')
|
4
|
-
require 'speech'
|
5
|
-
|
6
|
-
class SpeechAudioToTextTest < Test::Unit::TestCase
|
7
|
-
def test_audio_to_text
|
8
|
-
audio = Speech::AudioToText.new("samples/i-like-pickles.wav")
|
9
|
-
captured_json = audio.to_text
|
10
|
-
assert captured_json
|
11
|
-
assert captured_json.key?("captured_json")
|
12
|
-
assert !captured_json['captured_json'].empty?
|
13
|
-
assert_equal ['captured_json', 'confidence'], captured_json.keys.sort
|
14
|
-
assert_equal "I like pickles", captured_json['captured_json'].flatten.first
|
15
|
-
assert captured_json['confidence'] > 0.9
|
16
|
-
# {"captured_json"=>[["I like pickles", 0.92731786]], "confidence"=>0.92731786}
|
17
|
-
# puts captured_json.inspect
|
18
|
-
ensure
|
19
|
-
audio.clean
|
20
|
-
end
|
21
|
-
end
|
@@ -1 +0,0 @@
|
|
1
|
-
{"captured_json":[["I like pickles",0.92731786]],"confidence":0.92731786}
|