Update app.py

app.py

@@ -27,6 +27,7 @@ speaker_embeddings = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze
 
 def translate(audio):
     outputs = asr_pipe(audio, max_new_tokens=256, generate_kwargs={"task": "transcribe", "language": "nl"})
+    print ("Translated text", outputs["text"][:600])
     return outputs["text"][:600]
 
 
@@ -39,7 +40,6 @@ def synthesise(text):
 def speech_to_speech_translation(audio):
     translated_text = translate(audio)
     synthesised_speech = synthesise(translated_text)
-    synthesised_speech = synthesised_speech[:1800]
     synthesised_speech = (synthesised_speech.numpy() * 32767).astype(np.int16)
     return 16000, synthesised_speech