Update app.py

app.py

@@ -256,6 +256,22 @@ chat_demo_interface = gr.ChatInterface(
     theme='NoCrypt/miku'
 )
 
+from transformers import pipeline
+
+pipe = pipeline("automatic-speech-recognition", model="openai/whisper-large-v3-turbo")
+
+def transcribe_speech(filepath):
+    output = pipe(
+        filepath,
+        max_new_tokens=256,
+        generate_kwargs={
+            "task": "transcribe",
+        },  
+        chunk_length_s=30,
+        batch_size=1,
+    )
+    return output["text"]
+    
 mic_transcribe = gr.Interface(
     fn=transcribe_speech,
     inputs=gr.Audio(sources="microphone", type="filepath"),