sphinxtrain-ruby 0.0.1
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.
- checksums.yaml +7 -0
- data/.gitignore +23 -0
- data/.rspec +2 -0
- data/.travis.yml +31 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +51 -0
- data/Rakefile +9 -0
- data/bin/sphinxtrain-ruby +5 -0
- data/lib/sphinxtrain-ruby.rb +1 -0
- data/lib/sphinxtrain.rb +13 -0
- data/lib/sphinxtrain/analyser.rb +37 -0
- data/lib/sphinxtrain/map_adapter.rb +65 -0
- data/lib/sphinxtrain/trainer.rb +128 -0
- data/lib/sphinxtrain/training_decoder.rb +22 -0
- data/lib/sphinxtrain/version.rb +3 -0
- data/spec/spec_helper.rb +89 -0
- data/sphinxtrain-ruby.gemspec +28 -0
- metadata +147 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 4a9fb198c5caf9b81b6cbd645e86850c3e615517
|
4
|
+
data.tar.gz: 640907aaafb8a83d0a1e8ffe41ac301704964421
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: a3d64a1a77606bc4f2f5adbec12f549d8e366d8955e7c30194c3921175bc1b55d22cd232f284f1386810a2b02ce85212b71776057dbc02000d063e379aae1f59
|
7
|
+
data.tar.gz: f9d858fddae5f06562c7de6f80ccedbddccd7f0d401ccda81faee617350314766c8cc7baf464f57edaec2868a3eddb3380769ccd20c57fabae655f128d56e5b7
|
data/.gitignore
ADDED
@@ -0,0 +1,23 @@
|
|
1
|
+
*.gem
|
2
|
+
*.rbc
|
3
|
+
.bundle
|
4
|
+
.config
|
5
|
+
.yardoc
|
6
|
+
Gemfile.lock
|
7
|
+
InstalledFiles
|
8
|
+
_yardoc
|
9
|
+
coverage
|
10
|
+
doc/
|
11
|
+
lib/bundler/man
|
12
|
+
pkg
|
13
|
+
rdoc
|
14
|
+
spec/reports
|
15
|
+
test/tmp
|
16
|
+
test/version_tmp
|
17
|
+
tmp
|
18
|
+
*.bundle
|
19
|
+
*.so
|
20
|
+
*.o
|
21
|
+
*.a
|
22
|
+
mkmf.log
|
23
|
+
.DS_Store
|
data/.rspec
ADDED
data/.travis.yml
ADDED
@@ -0,0 +1,31 @@
|
|
1
|
+
language: ruby
|
2
|
+
rvm:
|
3
|
+
- 2.1.2
|
4
|
+
- 2.0.0
|
5
|
+
- 1.9.3
|
6
|
+
- rbx-2.2.9
|
7
|
+
- jruby-1.7.16
|
8
|
+
before_install:
|
9
|
+
- sudo apt-get update -qq
|
10
|
+
- sudo apt-get install -y swig
|
11
|
+
- git clone https://github.com/cmusphinx/sphinxbase.git
|
12
|
+
- cd sphinxbase
|
13
|
+
- ./autogen.sh
|
14
|
+
- ./configure
|
15
|
+
- make
|
16
|
+
- sudo make install
|
17
|
+
- cd ..
|
18
|
+
- git clone https://github.com/cmusphinx/pocketsphinx.git
|
19
|
+
- cd pocketsphinx
|
20
|
+
- ./autogen.sh
|
21
|
+
- ./configure
|
22
|
+
- make
|
23
|
+
- sudo make install
|
24
|
+
- cd ..
|
25
|
+
- git clone https://github.com/cmusphinx/sphinxtrain.git
|
26
|
+
- cd sphinxtrain
|
27
|
+
- ./autogen.sh
|
28
|
+
- ./configure
|
29
|
+
- sudo make install
|
30
|
+
- cd ..
|
31
|
+
- sudo ldconfig
|
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2014 Howard Wilson
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,51 @@
|
|
1
|
+
# sphinxtrain-ruby
|
2
|
+
|
3
|
+
[](https://travis-ci.org/watsonbox/sphinxtrain-ruby)
|
4
|
+
|
5
|
+
Toolkit for training/adapting CMU Sphinx acoustic models.
|
6
|
+
|
7
|
+
The main goal is to help with [adapting existing acoustic models](http://cmusphinx.sourceforge.net/wiki/tutorialadapt) to a specific speaker/accent. Currently only the English [Voxforge](http://voxforge.org/) model is supported as a base - in fact [an adapted one](http://grasch.net/node/21) created by Peter Grasch in 2013 using the most up to date training data available at that time. I can confirm his results of a few percent performance increase over Voxforge 0.4 for my accent at least (British English).
|
8
|
+
|
9
|
+
|
10
|
+
## Installation
|
11
|
+
|
12
|
+
Add this line to your application's Gemfile:
|
13
|
+
|
14
|
+
```ruby
|
15
|
+
gem 'sphinxtrain-ruby'
|
16
|
+
```
|
17
|
+
|
18
|
+
And then execute:
|
19
|
+
|
20
|
+
```bash
|
21
|
+
$ bundle
|
22
|
+
```
|
23
|
+
|
24
|
+
Or install it yourself as:
|
25
|
+
|
26
|
+
```bash
|
27
|
+
$ gem install sphinxtrain-ruby
|
28
|
+
```
|
29
|
+
|
30
|
+
|
31
|
+
## Usage
|
32
|
+
|
33
|
+
Run `sphinxtrain-ruby` from the command line and follow the instructions. See some example output [here](https://github.com/watsonbox/sphinxtrain-ruby/wiki/Example-Output).
|
34
|
+
|
35
|
+
|
36
|
+
## To Do
|
37
|
+
|
38
|
+
- [ ] Add support for different data sets, not just the example from CPU Sphinx
|
39
|
+
- [ ] Allow re-recording when mistakes are made
|
40
|
+
- [ ] Re-factor code and add specs
|
41
|
+
- [ ] Consider using actual libs rather than command line tools for adapting model
|
42
|
+
- [ ] Make command line wget downloads less verbose
|
43
|
+
|
44
|
+
|
45
|
+
## Contributing
|
46
|
+
|
47
|
+
1. Fork it ( https://github.com/watsonbox/sphinxtrain-ruby/fork )
|
48
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
49
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
50
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
51
|
+
5. Create a new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require 'sphinxtrain'
|
data/lib/sphinxtrain.rb
ADDED
@@ -0,0 +1,13 @@
|
|
1
|
+
require "pocketsphinx-ruby"
|
2
|
+
require "colorize"
|
3
|
+
require "word_aligner"
|
4
|
+
|
5
|
+
require "sphinxtrain/version"
|
6
|
+
require "sphinxtrain/analyser"
|
7
|
+
require "sphinxtrain/map_adapter"
|
8
|
+
require "sphinxtrain/training_decoder"
|
9
|
+
require "sphinxtrain/trainer"
|
10
|
+
|
11
|
+
module Sphinxtrain
|
12
|
+
# Your code goes here...
|
13
|
+
end
|
@@ -0,0 +1,37 @@
|
|
1
|
+
module Sphinxtrain
|
2
|
+
class Analyser
|
3
|
+
def initialize(model)
|
4
|
+
configuration['hmm'] = model
|
5
|
+
configuration['seed'] = 1 # Ensure deterministic results
|
6
|
+
end
|
7
|
+
|
8
|
+
def analyse(sentences_file, recordings_dir)
|
9
|
+
total = 0
|
10
|
+
|
11
|
+
File.open(sentences_file).each_line.with_index do |transcription, index|
|
12
|
+
transcription = transcription.downcase.gsub(/[,\.]/, '')
|
13
|
+
file_path = File.join(recordings_dir, "arctic_#{(index + 1).to_s.rjust(4, "0")}.raw")
|
14
|
+
decoder.decode file_path
|
15
|
+
hypothesis = decoder.hypothesis
|
16
|
+
error_rate = WordAligner.align(transcription, hypothesis)
|
17
|
+
total += error_rate.percentage_accurate
|
18
|
+
|
19
|
+
if block_given?
|
20
|
+
yield transcription, hypothesis, error_rate.percentage_accurate
|
21
|
+
end
|
22
|
+
end
|
23
|
+
|
24
|
+
total / 20
|
25
|
+
end
|
26
|
+
|
27
|
+
private
|
28
|
+
|
29
|
+
def configuration
|
30
|
+
@configuration ||= Pocketsphinx::Configuration.default
|
31
|
+
end
|
32
|
+
|
33
|
+
def decoder
|
34
|
+
@decoder ||= Pocketsphinx::Decoder.new(configuration)
|
35
|
+
end
|
36
|
+
end
|
37
|
+
end
|
@@ -0,0 +1,65 @@
|
|
1
|
+
module Sphinxtrain
|
2
|
+
class MapAdapter
|
3
|
+
SPHINX_FE_COMMAND = "sphinx_fe"
|
4
|
+
BW_COMMAND = "/usr/local/Cellar/cmu-sphinxtrain/HEAD/libexec/sphinxtrain/bw"
|
5
|
+
MAP_ADAPT_COMMAND = "/usr/local/Cellar/cmu-sphinxtrain/HEAD/libexec/sphinxtrain/map_adapt"
|
6
|
+
|
7
|
+
attr_accessor :old_model, :new_model, :recordings_dir, :sentences_transcription, :sentences_files, :sentences_dict
|
8
|
+
|
9
|
+
def initialize(old_model:, new_model:, recordings_dir:, sentences_transcription:, sentences_files:, sentences_dict:)
|
10
|
+
self.old_model = old_model
|
11
|
+
self.new_model = new_model
|
12
|
+
self.recordings_dir = recordings_dir
|
13
|
+
self.sentences_transcription = sentences_transcription
|
14
|
+
self.sentences_files = sentences_files
|
15
|
+
self.sentences_dict = sentences_dict
|
16
|
+
end
|
17
|
+
|
18
|
+
def adapt
|
19
|
+
`#{SPHINX_FE_COMMAND} \
|
20
|
+
-argfile #{new_model_file 'feat.params'} \
|
21
|
+
-samprate 16000 \
|
22
|
+
-c #{sentences_files} \
|
23
|
+
-di #{recordings_dir} \
|
24
|
+
-do #{recordings_dir} \
|
25
|
+
-ei raw \
|
26
|
+
-eo mfc \
|
27
|
+
-seed 1 > /dev/null 2>&1`
|
28
|
+
|
29
|
+
`#{BW_COMMAND} \
|
30
|
+
-hmmdir #{new_model} \
|
31
|
+
-moddeffn #{new_model_file 'mdef'} \
|
32
|
+
-ts2cbfn ".cont." \
|
33
|
+
-feat 1s_c_d_dd \
|
34
|
+
-cmn current \
|
35
|
+
-agc none \
|
36
|
+
-dictfn #{sentences_dict} \
|
37
|
+
-ctlfn #{sentences_files} \
|
38
|
+
-lsnfn #{sentences_transcription} \
|
39
|
+
-accumdir #{recordings_dir} \
|
40
|
+
-lda #{new_model_file 'feature_transform'} \
|
41
|
+
-cepdir #{recordings_dir} > /dev/null 2>&1`
|
42
|
+
|
43
|
+
`#{MAP_ADAPT_COMMAND} \
|
44
|
+
-meanfn #{old_model_file 'means'} \
|
45
|
+
-varfn #{old_model_file 'variances'} \
|
46
|
+
-mixwfn #{old_model_file 'mixture_weights'} \
|
47
|
+
-tmatfn #{old_model_file 'transition_matrices'} \
|
48
|
+
-accumdir #{recordings_dir} \
|
49
|
+
-mapmeanfn #{new_model_file 'means'} \
|
50
|
+
-mapvarfn #{new_model_file 'variances'} \
|
51
|
+
-mapmixwfn #{new_model_file 'mixture_weights'} \
|
52
|
+
-maptmatfn #{new_model_file 'transition_matrices'} > /dev/null 2>&1`
|
53
|
+
end
|
54
|
+
|
55
|
+
private
|
56
|
+
|
57
|
+
def old_model_file(file)
|
58
|
+
File.join(old_model, file)
|
59
|
+
end
|
60
|
+
|
61
|
+
def new_model_file(file)
|
62
|
+
File.join(new_model, file)
|
63
|
+
end
|
64
|
+
end
|
65
|
+
end
|
@@ -0,0 +1,128 @@
|
|
1
|
+
require 'fileutils'
|
2
|
+
|
3
|
+
module Sphinxtrain
|
4
|
+
class Trainer
|
5
|
+
BASE_DIR = File.join(Dir.home, '.sphinxtrain-ruby')
|
6
|
+
#VOXFORGE_URL = "http://downloads.sourceforge.net/project/cmusphinx/Acoustic%20and%20Language%20Models/English%20Voxforge/voxforge-en-0.4.tar.gz"
|
7
|
+
VOXFORGE_URL = "http://files.kde.org/accessibility/Simon/am/voxforge_en_sphinx.cd_cont_5000.tar.gz"
|
8
|
+
VOXFORGE_FILE = File.basename(VOXFORGE_URL)
|
9
|
+
VOXFORGE_FOLDER = File.basename(VOXFORGE_FILE, '.tar.gz')
|
10
|
+
#VOXFORGE_MODEL = File.join(BASE_DIR, VOXFORGE_FOLDER, "model_parameters/voxforge_en_sphinx.cd_cont_5000")
|
11
|
+
VOXFORGE_MODEL = VOXFORGE_FOLDER
|
12
|
+
RECORDINGS_DIR = File.join(BASE_DIR, 'recordings')
|
13
|
+
NEW_MODEL = File.join(BASE_DIR, 'new_model')
|
14
|
+
|
15
|
+
def train
|
16
|
+
Pocketsphinx.disable_logging
|
17
|
+
|
18
|
+
Dir.mkdir BASE_DIR rescue Errno::EEXIST
|
19
|
+
Dir.chdir BASE_DIR do
|
20
|
+
download_voxforge unless File.exist?(VOXFORGE_FILE)
|
21
|
+
download_assets unless arctic_file(:txt, :listoffiles, :transcription, :dic).all? { |f| File.exist? f }
|
22
|
+
record_sentences unless Dir.exist?(RECORDINGS_DIR)
|
23
|
+
|
24
|
+
analyse_model VOXFORGE_MODEL
|
25
|
+
|
26
|
+
duplicate_model
|
27
|
+
adapt_model
|
28
|
+
|
29
|
+
analyse_model NEW_MODEL
|
30
|
+
end
|
31
|
+
end
|
32
|
+
|
33
|
+
private
|
34
|
+
|
35
|
+
def download_voxforge
|
36
|
+
log "=> Downloading Voxforge English 0.4 Acoustic Model..."
|
37
|
+
`wget #{VOXFORGE_URL}`
|
38
|
+
`tar xfz #{VOXFORGE_FILE}`
|
39
|
+
end
|
40
|
+
|
41
|
+
def download_assets
|
42
|
+
log "=> Downloading CMU ARCTIC Example Sentences..."
|
43
|
+
|
44
|
+
arctic_file(:txt, :listoffiles, :transcription, :dic).each do |file|
|
45
|
+
`wget http://www.speech.cs.cmu.edu/cmusphinx/moindocs/#{file} -O #{file}`
|
46
|
+
end
|
47
|
+
end
|
48
|
+
|
49
|
+
def arctic_file(*keys)
|
50
|
+
keys.length == 1 ? "arctic20.#{keys.first}" : keys.map { |k| arctic_file k }
|
51
|
+
end
|
52
|
+
|
53
|
+
def record_sentences
|
54
|
+
log "=> Recording sentences..."
|
55
|
+
Dir.mkdir RECORDINGS_DIR unless Dir.exist?(RECORDINGS_DIR)
|
56
|
+
|
57
|
+
recognizer = Pocketsphinx::LiveSpeechRecognizer.new
|
58
|
+
decoder = TrainingDecoder.new(recognizer.decoder)
|
59
|
+
recognizer.decoder = decoder
|
60
|
+
|
61
|
+
# Initialize the decoder and microphone
|
62
|
+
recognizer.decoder.ps_decoder
|
63
|
+
recognizer.recordable
|
64
|
+
|
65
|
+
File.open(arctic_file(:txt), 'r').lines.each_with_index do |sentence, index|
|
66
|
+
puts "SAY: #{sentence}"
|
67
|
+
puts "Press ENTER to continue"
|
68
|
+
gets
|
69
|
+
|
70
|
+
# Small delay to avoid capturing audio connected with keypress
|
71
|
+
sleep 0.2
|
72
|
+
|
73
|
+
# Record a single utterance captured by TrainingDecoder
|
74
|
+
recognizer.recognize do |speech|
|
75
|
+
save_audio decoder.last_utterance, index
|
76
|
+
break
|
77
|
+
end
|
78
|
+
|
79
|
+
puts "Saved audio\n\n"
|
80
|
+
end
|
81
|
+
end
|
82
|
+
|
83
|
+
def save_audio(data, sentence_index)
|
84
|
+
raise "Can't save empty audio data" if data.nil? || data.empty?
|
85
|
+
|
86
|
+
File.open(File.join(RECORDINGS_DIR, "arctic_#{(sentence_index + 1).to_s.rjust(4, "0")}.raw"), "wb") do |file|
|
87
|
+
file.write data
|
88
|
+
end
|
89
|
+
end
|
90
|
+
|
91
|
+
def analyse_model(model)
|
92
|
+
log "=> Analysing acoustic model...\n"
|
93
|
+
|
94
|
+
result = Analyser.new(model).analyse(arctic_file(:txt), RECORDINGS_DIR) do |transcription, hypothesis, accuracy|
|
95
|
+
puts " ACTUAL: #{transcription}"
|
96
|
+
puts " RECORD: #{hypothesis}"
|
97
|
+
puts " RESULT: #{accuracy}\n\n"
|
98
|
+
end
|
99
|
+
|
100
|
+
puts " OVERALL: #{result}\n\n"
|
101
|
+
end
|
102
|
+
|
103
|
+
def duplicate_model
|
104
|
+
log "=> Duplicating Voxforge acoustic model..."
|
105
|
+
|
106
|
+
FileUtils.rm_rf(NEW_MODEL) if Dir.exist?(NEW_MODEL)
|
107
|
+
FileUtils.cp_r(VOXFORGE_MODEL, NEW_MODEL)
|
108
|
+
end
|
109
|
+
|
110
|
+
# Follows process described here: http://cmusphinx.sourceforge.net/wiki/tutorialadapt
|
111
|
+
def adapt_model
|
112
|
+
log "=> Adapting Voxforge acoustic model..."
|
113
|
+
|
114
|
+
MapAdapter.new(
|
115
|
+
old_model: VOXFORGE_MODEL,
|
116
|
+
new_model: NEW_MODEL,
|
117
|
+
recordings_dir: RECORDINGS_DIR,
|
118
|
+
sentences_transcription: arctic_file(:transcription),
|
119
|
+
sentences_files: arctic_file(:listoffiles),
|
120
|
+
sentences_dict: arctic_file(:dic)
|
121
|
+
).adapt
|
122
|
+
end
|
123
|
+
|
124
|
+
def log(message)
|
125
|
+
puts message.colorize(:green)
|
126
|
+
end
|
127
|
+
end
|
128
|
+
end
|
@@ -0,0 +1,22 @@
|
|
1
|
+
module Sphinxtrain
|
2
|
+
# Wrap a decoder to save the last utterance
|
3
|
+
class TrainingDecoder < SimpleDelegator
|
4
|
+
attr_accessor :data
|
5
|
+
attr_accessor :last_utterance
|
6
|
+
|
7
|
+
def start_utterance(*args)
|
8
|
+
self.data = ""
|
9
|
+
super
|
10
|
+
end
|
11
|
+
|
12
|
+
def end_utterance(*args)
|
13
|
+
self.last_utterance = data
|
14
|
+
super
|
15
|
+
end
|
16
|
+
|
17
|
+
def process_raw(buffer, size, *args)
|
18
|
+
super
|
19
|
+
self.data << buffer.get_bytes(0, size * 2)
|
20
|
+
end
|
21
|
+
end
|
22
|
+
end
|
data/spec/spec_helper.rb
ADDED
@@ -0,0 +1,89 @@
|
|
1
|
+
# This file was generated by the `rspec --init` command. Conventionally, all
|
2
|
+
# specs live under a `spec` directory, which RSpec adds to the `$LOAD_PATH`.
|
3
|
+
# The generated `.rspec` file contains `--require spec_helper` which will cause this
|
4
|
+
# file to always be loaded, without a need to explicitly require it in any files.
|
5
|
+
#
|
6
|
+
# Given that it is always loaded, you are encouraged to keep this file as
|
7
|
+
# light-weight as possible. Requiring heavyweight dependencies from this file
|
8
|
+
# will add to the boot time of your test suite on EVERY test run, even for an
|
9
|
+
# individual file that may not need all of that loaded. Instead, consider making
|
10
|
+
# a separate helper file that requires the additional dependencies and performs
|
11
|
+
# the additional setup, and require it from the spec files that actually need it.
|
12
|
+
#
|
13
|
+
# The `.rspec` file also contains a few flags that are not defaults but that
|
14
|
+
# users commonly want.
|
15
|
+
#
|
16
|
+
# See http://rubydoc.info/gems/rspec-core/RSpec/Core/Configuration
|
17
|
+
RSpec.configure do |config|
|
18
|
+
# rspec-expectations config goes here. You can use an alternate
|
19
|
+
# assertion/expectation library such as wrong or the stdlib/minitest
|
20
|
+
# assertions if you prefer.
|
21
|
+
config.expect_with :rspec do |expectations|
|
22
|
+
# This option will default to `true` in RSpec 4. It makes the `description`
|
23
|
+
# and `failure_message` of custom matchers include text for helper methods
|
24
|
+
# defined using `chain`, e.g.:
|
25
|
+
# be_bigger_than(2).and_smaller_than(4).description
|
26
|
+
# # => "be bigger than 2 and smaller than 4"
|
27
|
+
# ...rather than:
|
28
|
+
# # => "be bigger than 2"
|
29
|
+
expectations.include_chain_clauses_in_custom_matcher_descriptions = true
|
30
|
+
end
|
31
|
+
|
32
|
+
# rspec-mocks config goes here. You can use an alternate test double
|
33
|
+
# library (such as bogus or mocha) by changing the `mock_with` option here.
|
34
|
+
config.mock_with :rspec do |mocks|
|
35
|
+
# Prevents you from mocking or stubbing a method that does not exist on
|
36
|
+
# a real object. This is generally recommended, and will default to
|
37
|
+
# `true` in RSpec 4.
|
38
|
+
mocks.verify_partial_doubles = true
|
39
|
+
end
|
40
|
+
|
41
|
+
# The settings below are suggested to provide a good initial experience
|
42
|
+
# with RSpec, but feel free to customize to your heart's content.
|
43
|
+
=begin
|
44
|
+
# These two settings work together to allow you to limit a spec run
|
45
|
+
# to individual examples or groups you care about by tagging them with
|
46
|
+
# `:focus` metadata. When nothing is tagged with `:focus`, all examples
|
47
|
+
# get run.
|
48
|
+
config.filter_run :focus
|
49
|
+
config.run_all_when_everything_filtered = true
|
50
|
+
|
51
|
+
# Limits the available syntax to the non-monkey patched syntax that is recommended.
|
52
|
+
# For more details, see:
|
53
|
+
# - http://myronmars.to/n/dev-blog/2012/06/rspecs-new-expectation-syntax
|
54
|
+
# - http://teaisaweso.me/blog/2013/05/27/rspecs-new-message-expectation-syntax/
|
55
|
+
# - http://myronmars.to/n/dev-blog/2014/05/notable-changes-in-rspec-3#new__config_option_to_disable_rspeccore_monkey_patching
|
56
|
+
config.disable_monkey_patching!
|
57
|
+
|
58
|
+
# This setting enables warnings. It's recommended, but in some cases may
|
59
|
+
# be too noisy due to issues in dependencies.
|
60
|
+
config.warnings = true
|
61
|
+
|
62
|
+
# Many RSpec users commonly either run the entire suite or an individual
|
63
|
+
# file, and it's useful to allow more verbose output when running an
|
64
|
+
# individual spec file.
|
65
|
+
if config.files_to_run.one?
|
66
|
+
# Use the documentation formatter for detailed output,
|
67
|
+
# unless a formatter has already been configured
|
68
|
+
# (e.g. via a command-line flag).
|
69
|
+
config.default_formatter = 'doc'
|
70
|
+
end
|
71
|
+
|
72
|
+
# Print the 10 slowest examples and example groups at the
|
73
|
+
# end of the spec run, to help surface which specs are running
|
74
|
+
# particularly slow.
|
75
|
+
config.profile_examples = 10
|
76
|
+
|
77
|
+
# Run specs in random order to surface order dependencies. If you find an
|
78
|
+
# order dependency and want to debug it, you can fix the order by providing
|
79
|
+
# the seed, which is printed after each run.
|
80
|
+
# --seed 1234
|
81
|
+
config.order = :random
|
82
|
+
|
83
|
+
# Seed global randomization in this process using the `--seed` CLI option.
|
84
|
+
# Setting this allows you to use `--seed` to deterministically reproduce
|
85
|
+
# test failures related to randomization by passing the same `--seed` value
|
86
|
+
# as the one that triggered the failure.
|
87
|
+
Kernel.srand config.seed
|
88
|
+
=end
|
89
|
+
end
|
@@ -0,0 +1,28 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'sphinxtrain/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "sphinxtrain-ruby"
|
8
|
+
spec.version = Sphinxtrain::VERSION
|
9
|
+
spec.authors = ["Howard Wilson"]
|
10
|
+
spec.email = ["howard@watsonbox.net"]
|
11
|
+
spec.summary = %q{Toolkit for training/adapting CMU Sphinx acoustic models.}
|
12
|
+
spec.description = %q{Toolkit for training/adapting CMU Sphinx acoustic models.}
|
13
|
+
spec.homepage = ""
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files -z`.split("\x0")
|
17
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
18
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
19
|
+
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.add_dependency "pocketsphinx-ruby", "~> 0.1.1"
|
22
|
+
spec.add_dependency "word_aligner", "~> 0.1.2"
|
23
|
+
spec.add_dependency "colorize", "~> 0.7.3"
|
24
|
+
|
25
|
+
spec.add_development_dependency "bundler", "~> 1.6"
|
26
|
+
spec.add_development_dependency "rspec", "~> 3.1.0"
|
27
|
+
spec.add_development_dependency "rake"
|
28
|
+
end
|
metadata
ADDED
@@ -0,0 +1,147 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: sphinxtrain-ruby
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Howard Wilson
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2014-11-10 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: pocketsphinx-ruby
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: 0.1.1
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: 0.1.1
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: word_aligner
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: 0.1.2
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: 0.1.2
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: colorize
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: 0.7.3
|
48
|
+
type: :runtime
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: 0.7.3
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: bundler
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '1.6'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '1.6'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: rspec
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - "~>"
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: 3.1.0
|
76
|
+
type: :development
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - "~>"
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: 3.1.0
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: rake
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - ">="
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '0'
|
90
|
+
type: :development
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - ">="
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '0'
|
97
|
+
description: Toolkit for training/adapting CMU Sphinx acoustic models.
|
98
|
+
email:
|
99
|
+
- howard@watsonbox.net
|
100
|
+
executables:
|
101
|
+
- sphinxtrain-ruby
|
102
|
+
extensions: []
|
103
|
+
extra_rdoc_files: []
|
104
|
+
files:
|
105
|
+
- ".gitignore"
|
106
|
+
- ".rspec"
|
107
|
+
- ".travis.yml"
|
108
|
+
- Gemfile
|
109
|
+
- LICENSE.txt
|
110
|
+
- README.md
|
111
|
+
- Rakefile
|
112
|
+
- bin/sphinxtrain-ruby
|
113
|
+
- lib/sphinxtrain-ruby.rb
|
114
|
+
- lib/sphinxtrain.rb
|
115
|
+
- lib/sphinxtrain/analyser.rb
|
116
|
+
- lib/sphinxtrain/map_adapter.rb
|
117
|
+
- lib/sphinxtrain/trainer.rb
|
118
|
+
- lib/sphinxtrain/training_decoder.rb
|
119
|
+
- lib/sphinxtrain/version.rb
|
120
|
+
- spec/spec_helper.rb
|
121
|
+
- sphinxtrain-ruby.gemspec
|
122
|
+
homepage: ''
|
123
|
+
licenses:
|
124
|
+
- MIT
|
125
|
+
metadata: {}
|
126
|
+
post_install_message:
|
127
|
+
rdoc_options: []
|
128
|
+
require_paths:
|
129
|
+
- lib
|
130
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
131
|
+
requirements:
|
132
|
+
- - ">="
|
133
|
+
- !ruby/object:Gem::Version
|
134
|
+
version: '0'
|
135
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
136
|
+
requirements:
|
137
|
+
- - ">="
|
138
|
+
- !ruby/object:Gem::Version
|
139
|
+
version: '0'
|
140
|
+
requirements: []
|
141
|
+
rubyforge_project:
|
142
|
+
rubygems_version: 2.2.2
|
143
|
+
signing_key:
|
144
|
+
specification_version: 4
|
145
|
+
summary: Toolkit for training/adapting CMU Sphinx acoustic models.
|
146
|
+
test_files:
|
147
|
+
- spec/spec_helper.rb
|