[model] support audio (#6701)

* support qwen2_audio

* improve code

* lint

* fix

* fix

* fix

---------

Co-authored-by: hiyouga <hiyouga@buaa.edu.cn>
Former-commit-id: 5eacb5629e4d7733cd992a63747a1335f2c6a929

src/llamafactory/webui/chatter.py

@@ -172,6 +172,7 @@ class WebChatModel(ChatModel):
         tools: str,
         image: Optional[Any],
         video: Optional[Any],
+        audio: Optional[Any],
         max_new_tokens: int,
         top_p: float,
         temperature: float,
@@ -190,6 +191,7 @@ class WebChatModel(ChatModel):
             tools,
             images=[image] if image else None,
             videos=[video] if video else None,
+            audios=[audio] if audio else None,
             max_new_tokens=max_new_tokens,
             top_p=top_p,
             temperature=temperature,