Ali Tongyi Qianwen open-sources Qwen2-Audio 7B voice interaction model: free interaction without text input

AliThousand Questions on TongyiOpen Source There are two models in the Qwen2-Audio series: Qwen2-Audio-7B and Qwen2-Audio-7B-Instruct.

As a large-scale audio language model, Qwen2-Audio is able to accept various audio signal inputs and perform audio analysis or directly respond to text based on voice commands. It has two different audio interaction modes:

• Voice chat: Users can freely interact with Qwen2-Audio through voice.No text input required
• Audio analysis: Users can provide audio and text instructions to analyze the audio during the interaction

Officially tested on a series of benchmark datasets, Qwen2-Audio surpassed the previous best model.

The relevant links are as follows:

• Trial Link：https://huggingface.co/spaces/Qwen/Qwen2-Audio-Instruct-Demo
• Paper address:https://arxiv.org/abs/2407.10759
• Evaluation criteria:https://github.com/OFA-Sys/AIR-Bench
• Open Source Code:https://github.com/QwenLM/Qwen2-Audio