Update app.py
Browse files
app.py
CHANGED
@@ -7,7 +7,7 @@ from datetime import datetime
|
|
7 |
import os
|
8 |
import time
|
9 |
from pydub import AudioSegment
|
10 |
-
from IPython.display import Audio, display, Video, HTML
|
11 |
# import assemblyai as aai
|
12 |
from base64 import b64encode
|
13 |
import gradio as gr
|
@@ -149,16 +149,13 @@ def summarize(meeting_texts=meeting_texts):
|
|
149 |
minutes_of_meeting += summary
|
150 |
minutes_of_meeting = minutes_of_meeting.replace('User:', '').strip()
|
151 |
print("\n")
|
152 |
-
print(minutes_of_meeting)
|
153 |
return minutes_of_meeting
|
154 |
|
155 |
|
156 |
# Placeholder function for speech to text conversion
|
157 |
def speech_to_text(video):
|
158 |
print('Started transcribing')
|
159 |
-
# transcript = transcriber.transcribe(video).text
|
160 |
-
# print('transcript:', transcript)
|
161 |
-
# transcript = transcriber.transcribe(video).text
|
162 |
audio = AudioSegment.from_file(video, format="mp4")
|
163 |
audio.export('temp.mp3', format="mp3")
|
164 |
transcript= transcriber.transcribe('temp.mp3')['text']
|
@@ -181,14 +178,6 @@ def synthesize_speech(video, source_language,target_language):
|
|
181 |
file_format = 'audio/mpeg',
|
182 |
source_language = source_language,
|
183 |
target_language = target_language)
|
184 |
-
# mp4 = open(dub_video,'rb').read()
|
185 |
-
# video_url = "data:video/mp4;base64," + b64encode(mp4).decode()
|
186 |
-
# display(HTML("""
|
187 |
-
# <video width=400 controls>
|
188 |
-
# <source src="%s" type="video/mp4">
|
189 |
-
# </video>
|
190 |
-
# """ % video_url))
|
191 |
-
# print(dub_video)
|
192 |
return dub_video
|
193 |
|
194 |
# This function handles the processing when any participant speaks
|
@@ -221,22 +210,7 @@ def process_speaker(video, speaker_idx, n_participants, *language_list):
|
|
221 |
meeting_texts.append({f"Speaker_{speaker_idx+1}":outputs[0]})
|
222 |
else:
|
223 |
meeting_texts.append({f"Speaker_{speaker_idx+1}":outputs[1]})
|
224 |
-
|
225 |
-
|
226 |
-
# if i == speaker_idx:
|
227 |
-
# # outputs.append(transcript)
|
228 |
-
# outputs.insert(0, transcript)
|
229 |
-
# # outputs.insert(1, None)
|
230 |
-
# else:
|
231 |
-
# participant_language = language_codes[language_list[i]]
|
232 |
-
# print('participant_language:', participant_language)
|
233 |
-
# speaker_language = language_codes[language_list[speaker_idx]]
|
234 |
-
# print('speaker_language:', speaker_language)
|
235 |
-
|
236 |
-
# translated_text = translate_text(transcript, speaker_language, participant_language)
|
237 |
-
# dubbed_video = synthesize_speech(video, speaker_language, participant_language)
|
238 |
-
# outputs.append(translated_text)
|
239 |
-
# outputs.append(dubbed_video)
|
240 |
print(len(outputs))
|
241 |
print(outputs)
|
242 |
print('meeting_texts: ',meeting_texts)
|
|
|
7 |
import os
|
8 |
import time
|
9 |
from pydub import AudioSegment
|
10 |
+
# from IPython.display import Audio, display, Video, HTML
|
11 |
# import assemblyai as aai
|
12 |
from base64 import b64encode
|
13 |
import gradio as gr
|
|
|
149 |
minutes_of_meeting += summary
|
150 |
minutes_of_meeting = minutes_of_meeting.replace('User:', '').strip()
|
151 |
print("\n")
|
152 |
+
print("minutes_of_meeting:", minutes_of_meeting)
|
153 |
return minutes_of_meeting
|
154 |
|
155 |
|
156 |
# Placeholder function for speech to text conversion
|
157 |
def speech_to_text(video):
|
158 |
print('Started transcribing')
|
|
|
|
|
|
|
159 |
audio = AudioSegment.from_file(video, format="mp4")
|
160 |
audio.export('temp.mp3', format="mp3")
|
161 |
transcript= transcriber.transcribe('temp.mp3')['text']
|
|
|
178 |
file_format = 'audio/mpeg',
|
179 |
source_language = source_language,
|
180 |
target_language = target_language)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
181 |
return dub_video
|
182 |
|
183 |
# This function handles the processing when any participant speaks
|
|
|
210 |
meeting_texts.append({f"Speaker_{speaker_idx+1}":outputs[0]})
|
211 |
else:
|
212 |
meeting_texts.append({f"Speaker_{speaker_idx+1}":outputs[1]})
|
213 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
214 |
print(len(outputs))
|
215 |
print(outputs)
|
216 |
print('meeting_texts: ',meeting_texts)
|