Update app.py

app.py

@@ -29,7 +29,7 @@ def translate(audio):
     return transcription
 
 def synthesise(text):
-    print(text)
+    print("text",text)
     inputs = tokenizer_mms(text[0], return_tensors="pt")
     input_ids = inputs["input_ids"]
     with torch.no_grad():
@@ -43,7 +43,10 @@ def speech_to_speech_translation(audio):
     data_16 = librosa.resample(data_array, orig_sr=samplerate, target_sr=sampling_rate)
     translated_text = translate(data_16)
     synthesised_speech = synthesise(translated_text)
+    print("max_range",max_range)
     synthesised_speech = (synthesised_speech.numpy() * max_range).astype(np.int16)
+    print("sampling_rate",sampling_rate)
+    print("synthesised_speech",synthesised_speech)
     return sampling_rate, synthesised_speech