QwenLM/Qwen2-Audio
A large audio-language model from Alibaba's Qwen team capable of accepting speech and audio inputs for conversational interaction and audio analysis.
Not currently ranked — collecting fresh signals.
star history
Qwen2-Audio is a large-scale audio-language model that processes various audio signals and responds to speech instructions. It supports two interaction modes: free-form voice chat without text input, and audio analysis where users provide audio paired with text queries. The model is released in 7B parameter versions for both pretrained and instruction-tuned variants.
Frequently asked
- What is QwenLM/Qwen2-Audio?
- A large audio-language model from Alibaba's Qwen team capable of accepting speech and audio inputs for conversational interaction and audio analysis.
- Is Qwen2-Audio open source?
- Yes — QwenLM/Qwen2-Audio is an open-source project tracked on heatdrop.
- What language is Qwen2-Audio written in?
- QwenLM/Qwen2-Audio is primarily written in Python.
- How popular is Qwen2-Audio?
- QwenLM/Qwen2-Audio has 2.1k stars on GitHub.
- Where can I find Qwen2-Audio?
- QwenLM/Qwen2-Audio is on GitHub at https://github.com/QwenLM/Qwen2-Audio.