Update app.py

app.py

@@ -22,7 +22,7 @@ speaker_embeddings = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze
 
 
 def translate(audio):
-    outputs = asr_pipe(audio, max_new_tokens=256, generate_kwargs={"task": "translate", "language": "pl"})
+    outputs = asr_pipe(audio, max_new_tokens=256, generate_kwargs={"task": "transcribe", "language": "pl"})
     return outputs["text"]
 
 
@@ -49,13 +49,13 @@ Demo for cascaded speech-to-speech translation (STST), mapping from source speec
 
 demo = gr.Blocks()
 
-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,
-)
+# 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,
@@ -67,6 +67,6 @@ file_translate = gr.Interface(
 )
 
 with demo:
-    gr.TabbedInterface([mic_translate, file_translate], ["Microphone", "Audio File"])
+    gr.TabbedInterface([file_translate], ["Audio File"])
 
-demo.launch(share=True)
+demo.launch()