public push

Author: scotthavird

.gitignore

@@ -128,3 +128,4 @@ dmypy.json
 
 # Pyre type checker
 .pyre/
+data*

README.md

@@ -18,9 +18,34 @@ CONTENT_URL=https://augie-public-test.s3.amazonaws.com/89e5915c-cf8b-4f18-9b22-3
 docker-compose up --build
 ```
 
+## settings
+
+```python
+def request_transcript():
+    transcript_request = {
+        'audio_url': content_url,
+        #'filter_profanity': True,    # Profanity Filtering                  https://www.assemblyai.com/docs/core-transcription#profanity-filtering
+        #'punctuate': True,           # Automate Punctuation and Casing      https://www.assemblyai.com/docs/core-transcription#automatic-punctuation-and-casing
+        #'language_detection': True,  # Automatic Language Detection         https://www.assemblyai.com/docs/core-transcription#automatic-language-detection
+        #'auto_highlights': True,     # Detect Important Phrases and Words   https://www.assemblyai.com/docs/audio-intelligence#detect-important-phrases-and-words
+        #'content_safety': True,      # Content Moderation                   https://www.assemblyai.com/docs/audio-intelligence#content-moderation
+        #'iab_categories': True,      # Topic Detection(IAB Categories)      https://www.assemblyai.com/docs/audio-intelligence#topic-detection-iab-classification
+        #'sentiment_analysis': True,  # Sentiment Analysis                   https://www.assemblyai.com/docs/audio-intelligence#sentiment-analysis
+        #'summary_type': 'bullets',   # Summary bullets                      https://www.assemblyai.com/docs/audio-intelligence#summarization
+        #'summary_type': 'gist',      # Summary gist
+        #'summary_type': 'headline',  # Summary headline
+        #'summary_type': 'paragraph', # Summary paragraph
+        #'auto_chapters': True,       # Automatic Chapters                   https://www.assemblyai.com/docs/audio-intelligence#auto-chapters
+        #'entity_detection': True,    # Entity Detection                     https://www.assemblyai.com/docs/audio-intelligence#entity-detection
+        'dual_channel': False
+    }
+```
+
 ## results
 
-### paragraph
+output will be saved to `data.*.*` files
+
+### paragraph example
 
 ```json
 [

docker-compose.yml

@@ -2,7 +2,7 @@ version: "3.7"
 services:
   operator:
     build: .
-    image: assemgly_ai:0.1.0
+    image: assembly_ai:0.1.0    
     env_file:
       - default.env
     volumes: 

main.py

@@ -18,19 +18,20 @@
 def request_transcript():
     transcript_request = {
         'audio_url': content_url,
-        'filter_profanity': True,    # Profanity Filtering                  https://www.assemblyai.com/docs/core-transcription#profanity-filtering
-        'punctuate': True,           # Automate Punctuation and Casing      https://www.assemblyai.com/docs/core-transcription#automatic-punctuation-and-casing
-        'language_detection': True,  # Automatic Language Detection         https://www.assemblyai.com/docs/core-transcription#automatic-language-detection
-        'auto_highlights': True,     # Detect Important Phrases and Words   https://www.assemblyai.com/docs/audio-intelligence#detect-important-phrases-and-words
-        'content_safety': True,      # Content Moderation                   https://www.assemblyai.com/docs/audio-intelligence#content-moderation
-        'iab_categories': True,      # Topic Detection(IAB Categories)      https://www.assemblyai.com/docs/audio-intelligence#topic-detection-iab-classification
-        'sentiment_analysis': True,  # Sentiment Analysis                   https://www.assemblyai.com/docs/audio-intelligence#sentiment-analysis
-        'summary_type': 'bullets',   # Summary bullets                      https://www.assemblyai.com/docs/audio-intelligence#summarization
+        #'filter_profanity': True,    # Profanity Filtering                  https://www.assemblyai.com/docs/core-transcription#profanity-filtering
+        #'punctuate': True,           # Automate Punctuation and Casing      https://www.assemblyai.com/docs/core-transcription#automatic-punctuation-and-casing
+        #'language_detection': True,  # Automatic Language Detection         https://www.assemblyai.com/docs/core-transcription#automatic-language-detection
+        #'auto_highlights': True,     # Detect Important Phrases and Words   https://www.assemblyai.com/docs/audio-intelligence#detect-important-phrases-and-words
+        #'content_safety': True,      # Content Moderation                   https://www.assemblyai.com/docs/audio-intelligence#content-moderation
+        #'iab_categories': True,      # Topic Detection(IAB Categories)      https://www.assemblyai.com/docs/audio-intelligence#topic-detection-iab-classification
+        #'sentiment_analysis': True,  # Sentiment Analysis                   https://www.assemblyai.com/docs/audio-intelligence#sentiment-analysis
+        #'summary_type': 'bullets',   # Summary bullets                      https://www.assemblyai.com/docs/audio-intelligence#summarization
         #'summary_type': 'gist',      # Summary gist
         #'summary_type': 'headline',  # Summary headline
         #'summary_type': 'paragraph', # Summary paragraph
-        'auto_chapters': True,       # Automatic Chapters                   https://www.assemblyai.com/docs/audio-intelligence#auto-chapters
-        'entity_detection': True,    # Entity Detection                     https://www.assemblyai.com/docs/audio-intelligence#entity-detection
+        #'auto_chapters': True,       # Automatic Chapters                   https://www.assemblyai.com/docs/audio-intelligence#auto-chapters
+        #'entity_detection': True,    # Entity Detection                     https://www.assemblyai.com/docs/audio-intelligence#entity-detection
+        'dual_channel': False
     }
     transcript_response = requests.post(
         transcript_endpoint,
@@ -80,7 +81,7 @@ def main():
     # save request transcript
     transcript_response = request_transcript()
     json_object = json.dumps(transcript_response, indent=4)    
-    with open('request.json', 'w') as outfile:
+    with open('data.request.json', 'w') as outfile:
         outfile.write(json_object)
 
     # poll and wait
@@ -89,31 +90,31 @@ def main():
 
     # save transcription
     json_object = json.dumps(transcription, indent=4)    
-    with open('transcription.json', 'w') as outfile:
+    with open('data.transcription.json', 'w') as outfile:
         outfile.write(json_object)
 
     # save paragraphs
     paragraphs = get_paragraphs(polling_endpoint)    
     json_object = json.dumps(paragraphs, indent=4)    
-    with open('paragraphs.json', 'w') as outfile:
+    with open('data.paragraphs.json', 'w') as outfile:
         outfile.write(json_object)
 
     # save sentences
     sentences = get_sentences(polling_endpoint)
     json_object = json.dumps(sentences, indent=4)    
-    with open('sentences.json', 'w') as outfile:
+    with open('data.sentences.json', 'w') as outfile:
         outfile.write(json_object)
 
     # save srt 
     response = requests.get(polling_endpoint + '/srt', headers=headers)
     response = response.text
-    with open('srt.txt', 'w') as outfile:
+    with open('data.srt.txt', 'w') as outfile:
         outfile.write(response)
 
     # save vtt
     response = requests.get(polling_endpoint + '/vtt', headers=headers)
     response = response.text
-    with open('vtt.txt', 'w') as outfile:
+    with open('data.vtt.txt', 'w') as outfile:
         outfile.write(response)
 
 if __name__ == '__main__':