code

app.py

@@ -1,4 +1,14 @@
 import gradio as gr
+from gradio_webrtc import WebRTC, AdditionalOutputs
+
+from io import BytesIO
+from urllib.request import urlopen
+import librosa
+from transformers import Qwen2AudioForConditionalGeneration, AutoProcessor
+
+processor = AutoProcessor.from_pretrained("Qwen/Qwen2-Audio-7B-Instruct")
+model = Qwen2AudioForConditionalGeneration.from_pretrained("Qwen/Qwen2-Audio-7B-Instruct", device_map="auto")
+
 
 def greet(name):
     return "Hello " + name + "!!"

requirements.txt

@@ -0,0 +1,2 @@
+gradio_webrtc[vad]==0.0.11a1
+transformers@git+https://github.com/huggingface/transformers