google_speech 0.3.3 → 0.4.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/google_speech.gemspec +1 -0
- data/lib/google_speech.rb +2 -0
- data/lib/google_speech/chunk.rb +6 -0
- data/lib/google_speech/chunk_factory.rb +8 -3
- data/lib/google_speech/transcriber.rb +28 -10
- data/lib/google_speech/version.rb +1 -1
- metadata +15 -1
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 6813210970cbd391fc353833b73cf483fecb35be
|
4
|
+
data.tar.gz: 9800a202fb0bb0a66cf6e74f921021cb1f89f4f8
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: f77c8400be4f09302c472fa3da92679ff557e8f1a44b1bf12830c76d233130e500bba99583e62d2921a7d8d6a5850fe717b716f923cd754f9b9a8e87ba52156b
|
7
|
+
data.tar.gz: c998ca0fee9037f8691ae0c68dd994b555a3c13073afde8f93d58e5e47f179555df5beb4f669356ef8bcff5297c5c7d1db379e98b016a3fc4dd6aef3457fca12
|
data/google_speech.gemspec
CHANGED
data/lib/google_speech.rb
CHANGED
data/lib/google_speech/chunk.rb
CHANGED
@@ -18,9 +18,14 @@ module GoogleSpeech
|
|
18
18
|
def each
|
19
19
|
pos = 0
|
20
20
|
while(pos < @original_duration) do
|
21
|
-
chunk =
|
22
|
-
|
23
|
-
|
21
|
+
chunk = nil
|
22
|
+
begin
|
23
|
+
chunk = Chunk.new(@original_file, @original_duration, pos, (@chunk_duration + @overlap), @rate)
|
24
|
+
yield chunk
|
25
|
+
pos = pos + [chunk.duration, @chunk_duration].min
|
26
|
+
ensure
|
27
|
+
chunk.close_file if chunk
|
28
|
+
end
|
24
29
|
end
|
25
30
|
end
|
26
31
|
|
@@ -2,6 +2,7 @@
|
|
2
2
|
|
3
3
|
require 'excon'
|
4
4
|
require 'json'
|
5
|
+
require 'uuid'
|
5
6
|
|
6
7
|
module GoogleSpeech
|
7
8
|
|
@@ -31,21 +32,38 @@ module GoogleSpeech
|
|
31
32
|
@last_ua = 0
|
32
33
|
end
|
33
34
|
|
35
|
+
def open_working_file
|
36
|
+
Utility.check_local_file(@original_file.path)
|
37
|
+
wf_path = random_file_name(@original_file.path)
|
38
|
+
FileUtils.ln(@original_file.path, wf_path)
|
39
|
+
File.open(wf_path, 'r') {|f|
|
40
|
+
yield f
|
41
|
+
}
|
42
|
+
FileUtils.rm(wf_path, :force=>true)
|
43
|
+
end
|
44
|
+
|
45
|
+
def random_file_name(path)
|
46
|
+
File.join(GoogleSpeech::TMP_FILE_DIR, File.basename(path) + '_' + UUID.generate + '.wav')
|
47
|
+
end
|
48
|
+
|
34
49
|
def transcribe
|
35
|
-
|
36
|
-
|
37
|
-
|
38
|
-
|
39
|
-
|
50
|
+
open_working_file do |working_file|
|
51
|
+
chunk_factory = ChunkFactory.new(working_file, options[:chunk_duration], options[:overlap], options[:rate])
|
52
|
+
chunk_factory.each{ |chunk|
|
53
|
+
result = chunk.to_hash
|
54
|
+
transcript = transcribe_data(chunk.data)
|
55
|
+
next unless transcript
|
40
56
|
|
41
|
-
|
57
|
+
result = result.merge(extract_result(transcript))
|
42
58
|
|
43
|
-
|
59
|
+
logger.debug "#{result[:start_time]}: #{(result[:confidence].to_f * 100).to_i}%: #{result[:text]}"
|
44
60
|
|
45
|
-
|
61
|
+
@results << result
|
62
|
+
|
63
|
+
sleep(options[:request_pause].to_i)
|
64
|
+
}
|
65
|
+
end
|
46
66
|
|
47
|
-
sleep(options[:request_pause].to_i)
|
48
|
-
}
|
49
67
|
@results
|
50
68
|
end
|
51
69
|
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: google_speech
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.4.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Andrew Kuklewicz
|
@@ -24,6 +24,20 @@ dependencies:
|
|
24
24
|
- - '>='
|
25
25
|
- !ruby/object:Gem::Version
|
26
26
|
version: '0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: uuid
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - '>='
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - '>='
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
27
41
|
- !ruby/object:Gem::Dependency
|
28
42
|
name: rake
|
29
43
|
requirement: !ruby/object:Gem::Requirement
|