speech_to_text 0.1.3 → 0.1.4
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/Gemfile.lock +1 -1
- data/README.md +1 -1
- data/abc.mp3 +0 -0
- data/lib/speech_to_text/util.rb +15 -9
- data/lib/speech_to_text/version.rb +1 -1
- data/webcams.webm +0 -0
- metadata +4 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 0601f9186723489cc821a5afe961b94925734a73586f134b43cd8c28ce6c4e68
|
4
|
+
data.tar.gz: 7f7fd338e9255e5357a6f6a684131559b386f8377617f33ede8c1b90c8d777de
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: e1f01caf754a1a015c7c82a2d8bf0e3112a7224859cbbf527d977a84cfc60b407cb9708cc756d63ebc175650282c64fb2f10c1de878aa7c38973dc392e492263
|
7
|
+
data.tar.gz: 3a9ddd6b49011df32d52d50b4f3c83b48c78e11b3e0fac458cb1e75231769e86fa1b4600735cd56d1bd8676b1987f4a605aa936dfc2832af5288d49d5c92f7cd
|
data/Gemfile.lock
CHANGED
data/README.md
CHANGED
@@ -148,7 +148,7 @@ once you get the myarray, you can execute command to create vtt file
|
|
148
148
|
vtt_file_path = "/home/bbb"
|
149
149
|
vtt_file_name = "vttfile.vtt"
|
150
150
|
|
151
|
-
SpeechToText::Util.write_to_webvtt(vtt_file_path,vtt_file_name,myarray)
|
151
|
+
SpeechToText::Util.write_to_webvtt(vtt_file_path: "vtt_file_path", vtt_file_name: "vtt_file_name", myarray: myarray, start_time: "5")
|
152
152
|
```
|
153
153
|
|
154
154
|
NOTE: if you choose 3playmedia then you don't need to create myarray, you will directly get the vtt file
|
data/abc.mp3
ADDED
Binary file
|
data/lib/speech_to_text/util.rb
CHANGED
@@ -36,8 +36,10 @@ module SpeechToText
|
|
36
36
|
# rubocop:disable Metrics/MethodLength
|
37
37
|
def self.write_to_webvtt(vtt_file_path:, # rubocop:disable Metrics/AbcSize
|
38
38
|
vtt_file_name:,
|
39
|
-
myarray
|
39
|
+
myarray:,
|
40
|
+
start_time:)
|
40
41
|
|
42
|
+
start_time = start_time.to_i
|
41
43
|
filename = "#{vtt_file_path}/#{vtt_file_name}"
|
42
44
|
file = File.open(filename, 'w')
|
43
45
|
file.puts "WEBVTT\n\n"
|
@@ -47,12 +49,12 @@ module SpeechToText
|
|
47
49
|
|
48
50
|
file.puts i / 30 + 1
|
49
51
|
if i + 28 < myarray.length
|
50
|
-
file.puts "#{seconds_to_timestamp myarray[i]} --> #{seconds_to_timestamp myarray[i + 28]}"
|
52
|
+
file.puts "#{seconds_to_timestamp (myarray[i] + start_time).to_i} --> #{seconds_to_timestamp (myarray[i + 28] + start_time).to_i}"
|
51
53
|
file.puts "#{myarray[i + 2]} #{myarray[i + 5]} #{myarray[i + 8]} #{myarray[i + 11]} #{myarray[i + 14]}"
|
52
54
|
file.puts "#{myarray[i + 17]} #{myarray[i + 20]} #{myarray[i + 23]} #{myarray[i + 26]} #{myarray[i + 29]}\n\n"
|
53
55
|
else
|
54
56
|
remainder = myarray.length - i
|
55
|
-
file.puts "#{seconds_to_timestamp myarray[i]} --> #{seconds_to_timestamp myarray[myarray.length - 2]}"
|
57
|
+
file.puts "#{seconds_to_timestamp (myarray[i] + start_time).to_i} --> #{seconds_to_timestamp (myarray[myarray.length - 2] + start_time).to_i}"
|
56
58
|
count = 0
|
57
59
|
flag = true
|
58
60
|
while count < remainder
|
@@ -120,15 +122,19 @@ module SpeechToText
|
|
120
122
|
audio_content_type:,
|
121
123
|
**duration)
|
122
124
|
# rubocop:enable Metrics/ParameterLists
|
125
|
+
|
123
126
|
if duration.empty?
|
124
127
|
video_to_audio_command = "ffmpeg -y -i #{video_file_path}/#{video_name}.#{video_content_type} -ac 1 -ar 16000 #{audio_file_path}/#{audio_name}.#{audio_content_type}"
|
125
128
|
system(video_to_audio_command.to_s)
|
126
|
-
elsif duration.
|
127
|
-
video_to_audio_command = "ffmpeg -y -ss #{0.to_i} -i #{video_file_path}/#{video_name}.#{video_content_type} -t #{duration
|
128
|
-
system(video_to_audio_command.to_s)
|
129
|
-
|
130
|
-
video_to_audio_command = "ffmpeg -y -ss #{duration
|
131
|
-
system(video_to_audio_command.to_s)
|
129
|
+
elsif duration[:start_time].nil? && duration[:end_time] != nil
|
130
|
+
video_to_audio_command = "ffmpeg -y -ss #{0.to_i} -i #{video_file_path}/#{video_name}.#{video_content_type} -t #{duration[:end_time]} -ac 1 -ar 16000 #{audio_file_path}/#{audio_name}.#{audio_content_type}"
|
131
|
+
system(video_to_audio_command.to_s)
|
132
|
+
elsif duration[:end_time].nil? && duration[:start_time] != nil
|
133
|
+
video_to_audio_command = "ffmpeg -y -ss #{duration[:start_time]} -i #{video_file_path}/#{video_name}.#{video_content_type} -ac 1 -ar 16000 #{audio_file_path}/#{audio_name}.#{audio_content_type}"
|
134
|
+
system(video_to_audio_command.to_s)
|
135
|
+
else
|
136
|
+
video_to_audio_command = "ffmpeg -y -ss #{duration[:start_time]} -i #{video_file_path}/#{video_name}.#{video_content_type} -to #{duration[:end_time]} -ac 1 -ar 16000 #{audio_file_path}/#{audio_name}.#{audio_content_type}"
|
137
|
+
system(video_to_audio_command.to_s)
|
132
138
|
end
|
133
139
|
|
134
140
|
end
|
data/webcams.webm
ADDED
Binary file
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: speech_to_text
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.1.
|
4
|
+
version: 0.1.4
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Richard Alam
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2019-11-
|
11
|
+
date: 2019-11-20 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|
@@ -94,6 +94,7 @@ files:
|
|
94
94
|
- LICENSE.txt
|
95
95
|
- README.md
|
96
96
|
- Rakefile
|
97
|
+
- abc.mp3
|
97
98
|
- bin/console
|
98
99
|
- bin/setup
|
99
100
|
- examples/3playmedia.rb
|
@@ -112,6 +113,7 @@ files:
|
|
112
113
|
- resources/test/test.json
|
113
114
|
- resources/test/video/video.mp4
|
114
115
|
- speech_to_text.gemspec
|
116
|
+
- webcams.webm
|
115
117
|
homepage: https://github.com/bigbluebutton/speech_to_text
|
116
118
|
licenses:
|
117
119
|
- MIT
|