Upload app.py

app.py

@@ -18,11 +18,11 @@ def translate(audio):
     outputs = pipe(
         audio,
         max_new_tokens=256,
-        generate_kwargs={"task": "transcribe", "language": "de"}
+        generate_kwargs={"task": "transcribe", "language": "es"}
     )
 
-model = VitsModel.from_pretrained("facebook/mms-tts-deu")
-tokenizer = VitsTokenizer.from_pretrained("facebook/mms-tts-deu")
+model = VitsModel.from_pretrained("facebook/mms-tts-spa")
+tokenizer = VitsTokenizer.from_pretrained("facebook/mms-tts-spa")
 
 def synthesise(text):
     inputs=tokenizer(text, return_tensors="pt")
@@ -41,17 +41,17 @@ demo = gr.Blocks()
 
 mic_translate = gr.Interface(
     fn=speech_to_speech_translation,
-    inputs=gr.Audio(sources="microphone", type="filepath"),
+    inputs=gr.Audio(source="microphone", type="filepath"),
     outputs=gr.Audio(label="Generated Speech", type="numpy"),
 )
 
 file_translate = gr.Interface(
     fn=speech_to_speech_translation,
-    inputs=gr.Audio(sources="upload", type="filepath"),
+    inputs=gr.Audio(source="upload", type="filepath"),
     outputs=gr.Audio(label="Generated Speech", type="numpy"),
 )
 
 with demo:
     gr.TabbedInterface([mic_translate, file_translate], ["Microphone", "Audio File"])
 
-demo.launch(share=True)
+demo.launch(debug=True)