{"library":"qwen-omni-utils","type":"library","category":null,"description":"Qwen Omni Language Model Utils is a Python library providing a toolkit to conveniently handle various types of audio and visual input for Qwen Omni multimodal models. It simplifies processing base64, URLs, and interleaved audio, images, and videos, offering an API-like experience. This library is current at version 0.0.9 and is actively maintained by the Qwen team as part of their multimodal large language model ecosystem.","language":"python","status":"active","version":"0.0.9","tags":["LLM","AI","Multimodal","Qwen","PyTorch","Utilities","Audio","Video","Image","Speech"],"install":[{"cmd":"pip install qwen-omni-utils -U","imports":["from qwen_omni_utils import process_mm_info"]},{"cmd":"pip install qwen-omni-utils[decord] -U\nsudo apt-get install ffmpeg","imports":[]}],"homepage":null,"github":"https://github.com/QwenLM/Qwen2-VL","docs":null,"changelog":null,"pypi":"https://pypi.org/project/qwen-omni-utils/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":25,"avg_install_s":16.4,"avg_import_s":null,"wheel_type":"wheel"},"url":"https://checklist.day/v1/registry/qwen-omni-utils/compatibility"},"provenance":{"verified_status":"install_fail","verified_at":"Sun Jun 28","last_verified":"Sun Jun 28","next_check":"Sun Jul 05","install_tag":null}}