{"task":"Speech Recognition","dataset":"AISHELL-2 Test Android","metric_names":["Word Error Rate (WER)"],"rows":[{"id":6935,"task":"Speech Recognition","parent_task":null,"dataset":"AISHELL-2 Test Android","model_name":"Qwen-Audio","metrics":{"Word Error Rate (WER)":"3.3"},"paper_url":"https://arxiv.org/abs/2311.07919v2","paper_title":"Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models","paper_date":"2023-11-14","code_links":[{"title":"alibaba-damo-academy/FunASR","url":"https://github.com/alibaba-damo-academy/FunASR"},{"title":"qwenlm/qwen-audio","url":"https://github.com/qwenlm/qwen-audio"}],"metrics_order":"[\"Word Error Rate (WER)\"]","area":"Audio","uses_additional_data":1,"source":"archive","tags":[]}]}