parse to float first

app.py

@@ -45,8 +45,8 @@ def transcribe(audio_file):
 
 
 def get_duration_ms(audio_file):
-    duration = mediainfo(audio_file)["duration"]
-    duration_ms = int(duration) * 1000
+    duration = mediainfo(audio_file)["duration"]  # a string in seconds
+    duration_ms = int(float(duration) * 1000)
     return duration_ms