Update app.py

app.py

@@ -753,12 +753,29 @@ with gr.Blocks(css=css, js=js, head=head) as demo:
         if len(locations) > 0:
             avg[0] = avg[0] / len(locations)
             avg[1] = avg[1] / len(locations)
-            
+
+        vtt = "WEBVTT\n\n"
+        h = [0,0]
+        m = [0,0]
+        s = [0,1]
+        
         for k, location in enumerate(locations):
             lat = vincenty((location["lat"], 0), (avg[0], 0)) * 1000
             lng = vincenty((0, location["lng"]), (0, avg[1])) * 1000
             locations[k]["lat"] = float(lat / 2.5 * 111 * np.sign(location["lat"]-avg[0]))
             locations[k]["lng"] = float(lng / 2.5 * 111 * np.sign(location["lng"]-avg[1]))
+
+            for l, sec in enumerate(s):
+                s[l] = s[l] + 1
+                if s[l] == 60:
+                    s[l] = 0
+                    m[l] = m[l] + 1
+                if m[l] == 60:
+                    m[l] = 0
+                    h[l] = h[l] + 1
+                
+            vtt = vtt + str(k+1) + "\n" + str(h[0]).zfill(2) + ":" + str(m[0]).zfill(2) + ":" + str(s[0]).zfill(2) + ".000 --> " + str(h[1]).zfill(2) + ":" + str(m[1]).zfill(2) + ":" + str(s[1]).zfill(2) + ".000\n" + locations[k]["lat"] + "," + locations[k]["lng"] + " " + locations[k]["heading"] + "," + locations[k]["pitch"] + "\n\n"
+
         print(locations)
         # 2.5m is height of camera on google street view car, 
         # distance from center of sphere to pavement roughly 255 - 144 = 111 units
@@ -766,7 +783,7 @@ with gr.Blocks(css=css, js=js, head=head) as demo:
         # Process the video and get the path of the output video
         output_video_path = make_video(uploaded_video,encoder=model_type,blur_data=blurin,o=boffset,b=bsize)
 
-        return output_video_path + (json.dumps(locations),)
+        return output_video_path + vtt #(json.dumps(locations),)
 
     submit.click(on_submit, inputs=[input_video, model_type, blur_in, boffset, bsize, coords], outputs=[processed_video, processed_zip, output_frame, output_mask, output_depth, coords])