RamAnanth1 commited on
Commit
66f1e8b
·
1 Parent(s): 00684fc

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +65 -65
app.py CHANGED
@@ -23,7 +23,7 @@ def _read_file(filename, chunk_size=5242880):
23
  break
24
  yield data
25
 
26
- def get_transcript_url(url, audio_intelligence_options):
27
 
28
  # JSON that tells the API which file to trancsribe
29
  json={
@@ -92,72 +92,72 @@ def get_transcript_url(url, audio_intelligence_options):
92
 
93
  return transcription_result['text'], transcription_result['summary'], sentiment_analysis_result
94
 
95
- def get_transcript_file(filename):
96
 
97
- upload_response = requests.post(
98
- upload_endpoint,
99
- headers=headers,
100
- data=_read_file(filename))
101
 
102
- # JSON that tells the API which file to trancsribe
103
- json = {
104
- # URL of the audio file to process
105
- "audio_url": upload_response.json()['upload_url'],
106
-
107
- # Turn on speaker labels
108
- "speaker_labels": True,
109
-
110
- # Turn on custom vocabulary
111
- "word_boost": ["assembly ai"],
112
-
113
- # Turn on custom spelling
114
- "custom_spelling": [
115
- {"from": ["assembly AI"], "to": "AssemblyAI"},
116
- {"from": ["assembly AI's"], "to": "AssemblyAI's"}
117
- ],
118
-
119
- # Turn on PII Redaction and specify policies
120
- "redact_pii": True,
121
- "redact_pii_policies": ["drug", "injury", "person_name"],
122
- "redact_pii_audio": True,
123
-
124
- # Turn on Auto Highlights
125
- "auto_highlights": True,
126
-
127
- # Turn on Content Moderation
128
- "content_safety": True,
129
-
130
- # Turn on Topic Detection
131
- "iab_categories": True,
132
-
133
- # Turn on Sentiment Analysis
134
- "sentiment_analysis": True,
135
-
136
- # Turn on Summarization and specify configuration
137
- "summarization": True,
138
- "summary_model": "informative",
139
- "summary_type": "bullets",
140
-
141
- # Turn on Entity Detection
142
- "entity_detection": True,
143
- }
144
-
145
- response = requests.post(
146
- transcript_endpoint,
147
- json=json,
148
- headers=headers # Authorization to link this transcription with your account
149
- )
150
-
151
- polling_endpoint = f"https://api.assemblyai.com/v2/transcript/{response.json()['id']}"
152
- while True:
153
- transcription_result = requests.get(polling_endpoint, headers=headers).json()
154
- if transcription_result['status'] == 'completed':
155
- break
156
- elif transcription_result['status'] == 'error':
157
- raise RuntimeError(f"Transcription failed: {transcription_result['error']}")
158
- else:
159
- time.sleep(3)
160
- return transcription_result['text']
161
 
162
  audio_intelligence_list = [
163
  "Summarization",
 
23
  break
24
  yield data
25
 
26
+ def get_transcript_url(url):
27
 
28
  # JSON that tells the API which file to trancsribe
29
  json={
 
92
 
93
  return transcription_result['text'], transcription_result['summary'], sentiment_analysis_result
94
 
95
+ # def get_transcript_file(filename):
96
 
97
+ # upload_response = requests.post(
98
+ # upload_endpoint,
99
+ # headers=headers,
100
+ # data=_read_file(filename))
101
 
102
+ # # JSON that tells the API which file to trancsribe
103
+ # json = {
104
+ # # URL of the audio file to process
105
+ # "audio_url": upload_response.json()['upload_url'],
106
+
107
+ # # Turn on speaker labels
108
+ # "speaker_labels": True,
109
+
110
+ # # Turn on custom vocabulary
111
+ # "word_boost": ["assembly ai"],
112
+
113
+ # # Turn on custom spelling
114
+ # "custom_spelling": [
115
+ # {"from": ["assembly AI"], "to": "AssemblyAI"},
116
+ # {"from": ["assembly AI's"], "to": "AssemblyAI's"}
117
+ # ],
118
+
119
+ # # Turn on PII Redaction and specify policies
120
+ # "redact_pii": True,
121
+ # "redact_pii_policies": ["drug", "injury", "person_name"],
122
+ # "redact_pii_audio": True,
123
+
124
+ # # Turn on Auto Highlights
125
+ # "auto_highlights": True,
126
+
127
+ # # Turn on Content Moderation
128
+ # "content_safety": True,
129
+
130
+ # # Turn on Topic Detection
131
+ # "iab_categories": True,
132
+
133
+ # # Turn on Sentiment Analysis
134
+ # "sentiment_analysis": True,
135
+
136
+ # # Turn on Summarization and specify configuration
137
+ # "summarization": True,
138
+ # "summary_model": "informative",
139
+ # "summary_type": "bullets",
140
+
141
+ # # Turn on Entity Detection
142
+ # "entity_detection": True,
143
+ # }
144
+
145
+ # response = requests.post(
146
+ # transcript_endpoint,
147
+ # json=json,
148
+ # headers=headers # Authorization to link this transcription with your account
149
+ # )
150
+
151
+ # polling_endpoint = f"https://api.assemblyai.com/v2/transcript/{response.json()['id']}"
152
+ # while True:
153
+ # transcription_result = requests.get(polling_endpoint, headers=headers).json()
154
+ # if transcription_result['status'] == 'completed':
155
+ # break
156
+ # elif transcription_result['status'] == 'error':
157
+ # raise RuntimeError(f"Transcription failed: {transcription_result['error']}")
158
+ # else:
159
+ # time.sleep(3)
160
+ # return transcription_result['text']
161
 
162
  audio_intelligence_list = [
163
  "Summarization",