speech_to_text 0.1.4 → 0.1.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 0601f9186723489cc821a5afe961b94925734a73586f134b43cd8c28ce6c4e68
-  data.tar.gz: 7f7fd338e9255e5357a6f6a684131559b386f8377617f33ede8c1b90c8d777de
+  metadata.gz: 912dddca8963d0db76d95ca167a7a0935c264a39384c6baec8dc20c956b97f8a
+  data.tar.gz: bbdeaf426301438a7009e38d07c008c0253b18e1c56e61c2c063e678d7c17128
 SHA512:
-  metadata.gz: e1f01caf754a1a015c7c82a2d8bf0e3112a7224859cbbf527d977a84cfc60b407cb9708cc756d63ebc175650282c64fb2f10c1de878aa7c38973dc392e492263
-  data.tar.gz: 3a9ddd6b49011df32d52d50b4f3c83b48c78e11b3e0fac458cb1e75231769e86fa1b4600735cd56d1bd8676b1987f4a605aa936dfc2832af5288d49d5c92f7cd
+  metadata.gz: 2dc6bc04f997a4f4101b3b5c45de7e354d11eacac6d3f7ad217df4eabc0afa1a30c1584c9bcc4ba63ab8008914a0a37da8515bbb64a03fb7c1390a0701e726cf
+  data.tar.gz: 8980ccbe70389e5029a145a0a4bcfefa72b2e2f815f49daf42bb300291f7cd33e8b2da6f2a69dca79a548ea7225f7578d1199198b9bc8cc1556829fc464846d5

data/.gitignore

@@ -7,3 +7,8 @@
 /spec/reports/
 /tmp/
 *.gem
+*.mp3
+*.mp4
+*.webm
+*.wav
+*.flac

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    speech_to_text (0.1.4)
+    speech_to_text (0.1.5)
       google-cloud-speech (= 0.35.0)
       google-cloud-storage (= 1.18.2)
       ibm_watson (~> 0.18.2)

data/README.md

@@ -79,7 +79,7 @@ bucket_name could be any string
 
 file = SpeechToText::GoogleS2T.google_storage(audio_file_path,audio_name,audio_content_type,bucket_name)
 operation_name = SpeechToText::GoogleS2T.create_job(audio_name,audio_content_type,bucket_name,language_code)
-data = SpeechToText::GoogleS2T.check_job(operation_name)
+data = SpeechToText::GoogleS2T.check_status(operation_name)
 myarray = SpeechToText::GoogleS2T.create_array_google(data["results"])
 SpeechToText::GoogleS2T.delete_google_storage(bucket_name,audio_name,audio_content_type)
 ```

data/lib/speech_to_text/3playmedia.rb

@@ -11,12 +11,24 @@
 require 'json'
 require 'net/http'
 require 'uri'
+require 'open3'
 
 module SpeechToText
   module ThreePlaymediaS2T # rubocop:disable Style/Documentation
     def self.create_job(api_key, audio_file, name, create_job_file)
       cretae_job_command = "curl -X POST -F \"source_file=@#{audio_file}\" \"https://api.3playmedia.com/v3/files?api_key=#{api_key}&language_id=1&name=#{name}\" > #{create_job_file}"
-      system(cretae_job_command)
+      Open3.popen2e(cretae_job_command) do |stdin, stdout_err, wait_thr|
+        while line = stdout_err.gets
+          puts "#{line}"
+        end
+
+        exit_status = wait_thr.value
+        unless exit_status.success?
+          puts '---------------------'
+          puts "FAILED to execute --> #{cretae_job_command}"
+          puts '---------------------'
+        end
+      end
       file = File.open(create_job_file, 'r')
       response = JSON.load file
       job_id = response['data']['id']

data/lib/speech_to_text/deepspeech.rb

@@ -11,6 +11,7 @@
 require 'json'
 require 'net/http'
 require 'uri'
+require 'open3'
 require_relative 'util.rb'
 
 module SpeechToText
@@ -19,7 +20,20 @@ module SpeechToText
 
     def self.create_job(audio, server_url, jobdetails_json)
       request = "curl -F \"file=@#{audio}\" \"#{server_url}/deepspeech/createjob\" > #{jobdetails_json}"
-      system(request)
+      
+      Open3.popen2e(request) do |stdin, stdout_err, wait_thr|
+        while line = stdout_err.gets
+          puts "#{line}"
+        end
+
+        exit_status = wait_thr.value
+        unless exit_status.success?
+          puts '---------------------'
+          puts "FAILED to execute --> #{request}"
+          puts '---------------------'
+        end
+      end
+
       file = File.open(jobdetails_json, 'r')
       data = JSON.load file
       data['job_id']
@@ -42,7 +56,20 @@ module SpeechToText
     # used by deepspeech server only
     def self.generate_transcript(audio, json_file, model_path)
       deepspeech_command = "#{model_path}/deepspeech --model #{model_path}/models/output_graph.pbmm --alphabet #{model_path}/models/alphabet.txt --lm #{model_path}/models/lm.binary --trie #{model_path}/models/trie -e --audio #{audio} > #{json_file}"
-      system(deepspeech_command.to_s)
+      
+      Open3.popen2e(deepspeech_command) do |stdin, stdout_err, wait_thr|
+        while line = stdout_err.gets
+          puts "#{line}"
+        end
+
+        exit_status = wait_thr.value
+        unless exit_status.success?
+          puts '---------------------'
+          puts "FAILED to execute --> #{deepspeech_command}"
+          puts '---------------------'
+        end
+      end
+
     end
 
     # rubocop:disable Metrics/MethodLength

data/lib/speech_to_text/google.rb

@@ -70,18 +70,15 @@ module SpeechToText
       # construct a new operation object from the id
       speech = Google::Cloud::Speech.new(version: :v1p1beta1)
       operation2 = speech.get_operation operation_name
+      status = 'not found'
       if operation2.error?
         status = 'failed'
-        return status
-      end
-
-      if operation2.done?
+      elsif operation2.done?
         status = 'completed'
-        return status
+      else
+        status = 'inProgress'  
       end
-
-      status = 'inProgress'
-      status
+      return status
     end
 
     def self.get_words(operation_name)

data/lib/speech_to_text/speechmatics.rb

@@ -12,6 +12,7 @@ require_relative 'util.rb'
 require 'net/http'
 require 'uri'
 require 'json'
+require 'open3'
 
 module SpeechToText
   module SpeechmaticsS2T # rubocop:disable Style/Documentation
@@ -24,7 +25,20 @@ module SpeechToText
       # rubocop:enable Metrics/ParameterLists
       # rubocop:enable Naming/VariableName
       upload_audio = "curl -F data_file=@#{audio_file_path}/#{audio_name}.#{audio_content_type} -F model=#{model} \"https://api.speechmatics.com/v1.0/user/#{userID}/jobs/?auth_token=#{authKey}\" > #{jobID_json_file}"
-      system(upload_audio.to_s)
+      
+      Open3.popen2e(upload_audio) do |stdin, stdout_err, wait_thr|
+        while line = stdout_err.gets
+          puts "#{line}"
+        end
+
+        exit_status = wait_thr.value
+        unless exit_status.success?
+          puts '---------------------'
+          puts "FAILED to execute --> #{upload_audio}"
+          puts '---------------------'
+        end
+      end
+
       file = File.open(jobID_json_file)
       data = JSON.load file
       jobID = data['id'] # rubocop:disable Naming/VariableName

data/lib/speech_to_text/util.rb

@@ -8,6 +8,7 @@
 #
 # Copyright (c) 2019 BigBlueButton Inc. and by respective authors (see below).
 #
+require 'open3'
 
 module SpeechToText
   module Util # rubocop:disable Style/Documentation
@@ -122,21 +123,34 @@ module SpeechToText
                             audio_content_type:,
                             **duration)
       # rubocop:enable Metrics/ParameterLists
-        
+      video_to_audio_command = ''
       if duration.empty?
         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}"
-        system(video_to_audio_command.to_s)
       elsif duration[:start_time].nil? && duration[:end_time] != nil
         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}"
-        system(video_to_audio_command.to_s)
       elsif duration[:end_time].nil? && duration[:start_time] != nil
         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}"
-        system(video_to_audio_command.to_s) 
       else
-        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}"
-        system(video_to_audio_command.to_s) 
-      end
-        
+        video_to_audio_command = "ffmpeg -y -t #{duration[:end_time]} -i #{video_file_path}/#{video_name}.#{video_content_type} -ss #{duration[:start_time]} -ac 1 -ar 16000 #{audio_file_path}/#{audio_name}.#{audio_content_type}"
+      end  
+
+        Open3.popen2e(video_to_audio_command) do |stdin, stdout_err, wait_thr|
+          while line = stdout_err.gets
+            puts "#{line}"
+          end
+
+          exit_status = wait_thr.value
+          unless exit_status.success?
+            puts '---------------------'
+            puts "FAILED to execute --> #{video_to_audio_command}"
+            puts '---------------------'
+          end
+        end
+
+        #Open3.popen3(video_to_audio_command.to_s) do |stdin, stdout, stderr, wait_thr|
+        #  puts "stdout is:" + stdout.read
+        #  puts "stderr is:" + stderr.read
+        #end
     end
   end
 end

data/lib/speech_to_text/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module SpeechToText
-  VERSION = '0.1.4'
+  VERSION = '0.1.5'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: speech_to_text
 version: !ruby/object:Gem::Version
-  version: 0.1.4
+  version: 0.1.5
 platform: ruby
 authors:
 - Richard Alam
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2019-11-20 00:00:00.000000000 Z
+date: 2019-11-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -94,7 +94,6 @@ files:
 - LICENSE.txt
 - README.md
 - Rakefile
-- abc.mp3
 - bin/console
 - bin/setup
 - examples/3playmedia.rb
@@ -113,7 +112,6 @@ files:
 - resources/test/test.json
 - resources/test/video/video.mp4
 - speech_to_text.gemspec
-- webcams.webm
 homepage: https://github.com/bigbluebutton/speech_to_text
 licenses:
 - MIT