add time logging

app.py

@@ -1,6 +1,7 @@
 import gradio as gr
 import numpy as np
 from utils import load_model, normalize_text
+import time
 
 vits = load_model()
 
@@ -14,7 +15,13 @@ def text_to_speech(text):
         dtype=np.int64,
     )[None, :]
 
+    start = time.perf_counter()
     audio = vits.inference_onnx(text_inputs)
+    end = time.perf_counter()
+    inference_time = end - start
+    audio_length = audio.shape[1] / vits.config.audio.sample_rate
+    print('Inference time: {}'.format(inference_time))
+    print('Real time factor: {}'.format(inference_time / audio_length))
     return 16000, audio[0]