Update handler.py

handler.py

@@ -3,7 +3,7 @@ import numpy as np
 import torch
 from transformers import SpeechT5Processor, SpeechT5ForTextToSpeech, SpeechT5HifiGan
 from datasets import load_dataset
-#import soundfile as sf
+import time
 from typing import Dict, List, Any
 
 
@@ -34,22 +34,22 @@ class EndpointHandler:
     def __call__(self, data: Dict[str, Any]) -> Dict[str, Any]:
         
         given_text = data.get("inputs", "")
-                
+
+        start_time = time.time()
+
         inputs = self.processor(text=given_text, return_tensors="pt")
 
         speech = self.model.generate_speech(inputs["input_ids"], self.speaker_embeddings, vocoder=self.vocoder)
-
-        #filename = "current_sample.wav"
         
-        # Write the response audio to a file
-        #sf.write(filename, speech.numpy(), samplerate=16000)
+        run_time = time.time() - start_time
 
         # Return the expected response format
         return {
             "statusCode": 200,
             "body": {
                 "audio": speech.numpy(),  # Consider encoding this to a suitable format
-                "sampling_rate": 16000
+                "sampling_rate": 16000,
+                "time_to_generate": str(run_time)
             }
         }