improve the audio model accuracy of qwen2.5-omni (#3013)

Co-authored-by: Aleksandr Mokrov <aleksandr.mokrov@intel.com>

Author: openvino-dev-samples

notebooks/qwen2.5-omni-chatbot/qwen2.5-omni-chatbot.ipynb

@@ -86,7 +86,7 @@
     "\n",
     "\n",
     "pip_install(\n",
-    "    \"transformers>=4.52.0\",\n",
+    "    \"transformers==4.52.0\",\n",
     "    \"torchvision\",\n",
     "    \"accelerate\",\n",
     "    \"qwen-omni-utils[decord]\",\n",