Update app.py

app.py

@@ -28,14 +28,21 @@ def translate(audio):
 
 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)
+    speech = model.generate_speech(
+        inputs["input_ids"].to(device), speaker_embeddings.to(device), vocoder=vocoder
+    )
     return speech.cpu()
 
+target_dtype = np.int16
+max_range = np.iinfo(target_dtype).max
+
 
 def speech_to_speech_translation(audio):
+    target_dtype = np.int16
+    max_range = np.iinfo(target_dtype).max
     translated_text = translate(audio)
     synthesised_speech = synthesise(translated_text)
-    synthesised_speech = (synthesised_speech.numpy() * 32767).astype(np.int16)
+    synthesised_speech = (synthesised_speech.numpy() * max_range).astype(np.int16)
     return 16000, synthesised_speech
 
 
@@ -53,20 +60,17 @@ mic_translate = gr.Interface(
     fn=speech_to_speech_translation,
     inputs=gr.Audio(source="microphone", type="filepath"),
     outputs=gr.Audio(label="Generated Speech", type="numpy"),
-    title=title,
-    description=description,
 )
 
 file_translate = gr.Interface(
     fn=speech_to_speech_translation,
     inputs=gr.Audio(source="upload", type="filepath"),
     outputs=gr.Audio(label="Generated Speech", type="numpy"),
-    examples=[["./example.wav"]],
-    title=title,
-    description=description,
 )
 
+
 with demo:
     gr.TabbedInterface([mic_translate, file_translate], ["Microphone", "Audio File"])
 
+
 demo.launch()