{ "bomFormat": "CycloneDX", "specVersion": "1.6", "serialNumber": "urn:uuid:90513858-215d-425c-97d1-bde59706b20a", "version": 1, "metadata": { "timestamp": "2025-06-05T09:40:51.718854+00:00", "component": { "type": "machine-learning-model", "bom-ref": "Qwen/Qwen2-Audio-7B-Instruct-669d5826-ff6c-5431-bcb7-445d2e3ea82f", "name": "Qwen/Qwen2-Audio-7B-Instruct", "externalReferences": [ { "url": "https://huggingface.co/Qwen/Qwen2-Audio-7B-Instruct", "type": "documentation" } ], "modelCard": { "modelParameters": { "task": "audio-text-to-text", "architectureFamily": "qwen2_audio", "modelArchitecture": "Qwen2AudioForConditionalGeneration" }, "properties": [ { "name": "library_name", "value": "transformers" } ] }, "authors": [ { "name": "Qwen" } ], "licenses": [ { "license": { "id": "Apache-2.0", "url": "https://spdx.org/licenses/Apache-2.0.html" } } ], "description": "Qwen2-Audio is the new series of Qwen large audio-language models. Qwen2-Audio is capable of accepting various audio signal inputs and performing audio analysis or direct textual responses with regard to speech instructions. We introduce two distinct audio interaction modes:* voice chat: users can freely engage in voice interactions with Qwen2-Audio without text input;* audio analysis: users could provide audio and text instructions for analysis during the interaction;We release Qwen2-Audio-7B and Qwen2-Audio-7B-Instruct, which are pretrained model and chat model respectively.For more details, please refer to our [Blog](https://qwenlm.github.io/blog/qwen2-audio/), [GitHub](https://github.com/QwenLM/Qwen2-Audio), and [Report](https://www.arxiv.org/abs/2407.10759).
", "tags": [ "transformers", "safetensors", "qwen2_audio", "text2text-generation", "chat", "audio", "audio-text-to-text", "en", "arxiv:2407.10759", "arxiv:2311.07919", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ] } } }