Update handler.py

handler.py

@@ -23,11 +23,13 @@ class EndpointHandler():
         """
         # process input
         inputs = data.pop("inputs", data)
+
         audio_nparray = ffmpeg_read(inputs, SAMPLE_RATE)
         audio_tensor= torch.from_numpy(audio_nparray)
         
         # run inference pipeline
-        result = self.model.transcribe(audio_nparray)
+        result = self.model.transcribe(audio_nparray, language = 'russian',
+            verbose = True, response_format = 'srt', return_timestamps=True,word_timestamps = True)
 
         # postprocess the prediction
-        return {"text": result["text"]}
+        return [0,result,2]