Update app.py

app.py

@@ -1,3 +1,41 @@
+
+def translate(audio):
+    outputs = pipe(audio, generate_kwargs={"task": "translate","max_new_tokens":256})
+    return outputs["text"]
+
+from transformers import SpeechT5Processor, SpeechT5ForTextToSpeech, SpeechT5HifiGan
+
+processor = SpeechT5Processor.from_pretrained("microsoft/speecht5_tts")
+model = SpeechT5ForTextToSpeech.from_pretrained("microsoft/speecht5_tts")
+vocoder = SpeechT5HifiGan.from_pretrained("microsoft/speecht5_hifigan")
+
+model.to(device);
+vocoder.to(device);
+
+embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
+speaker_embeddings = torch.tensor(embeddings_dataset[6000]["xvector"]).unsqueeze(0)
+     
+
+def synthesise(text):
+    inputs = processor(text=text, return_tensors="pt")
+    speech = model.generate_speech(
+        inputs["input_ids"].to(device), speaker_embeddings.to(device), vocoder=vocoder
+    )
+    return speech.cpu()
+
+import numpy as np
+
+target_dtype = np.int16
+max_range = np.iinfo(target_dtype).max
+
+
+def speech_to_speech_translation(audio):
+    translated_text = translate(audio)
+    synthesised_speech = synthesise(translated_text)
+    synthesised_speech = (synthesised_speech.numpy() * max_range).astype(np.int16)
+    return 16000, synthesised_speech
+    
+
 import gradio as gr
 
 demo = gr.Interface(