Update app.py

app.py

@@ -24,15 +24,15 @@ def predict(audio_path, time_resolution):
     audio_tag_result = whisper.parse_at_label(result, language='follow_asr', top_k=5, p_threshold=-1, include_class_list=list(range(527)))
     # print(audio_tag_result)
 
-    # asr_output = ""
-    # for segment in result['segments']:
-    #   asr_output = asr_output + str(segment['start']) + 's-' + str(segment['end']) + 's: ' + segment['text'] + '\n'
-    # at_output = ""
-    # for segment in audio_tag_result:
-    #     print(segment)
-    #     at_output = at_output + str(segment['time']['start']) + 's-' + str(segment['time']['end']) + 's: ' + ','.join([x[0] for x in segment['audio tags']]) + '\n'
-    #     print(at_output)
-    asr_output, at_output = str(result["text"]), 'k'
+    asr_output = ""
+    for segment in result['segments']:
+      asr_output = asr_output + str(segment['start']) + 's-' + str(segment['end']) + 's: ' + segment['text'] + '\n'
+    at_output = ""
+    for segment in audio_tag_result:
+        print(segment)
+        at_output = at_output + str(segment['time']['start']) + 's-' + str(segment['time']['end']) + 's: ' + ','.join([x[0] for x in segment['audio tags']]) + '\n'
+        print(at_output)
+    #asr_output, at_output = str(result["text"]), 'k'
     return asr_output, at_output
 
 iface = gr.Interface(fn=predict,