SenseVoice open-source speech understanding model repository supports ASR, emotion recognition, and audio event detection
Original title:QwenAudio/SenseVoice
AI summary
SenseVoice is a foundational speech understanding model supporting ASR, language identification, speech emotion recognition, and audio event detection. The released SenseVoiceSmall checkpoint supports Mandarin, Cantonese, English, Japanese, and Korean and outputs emotion and event labels; using a non-autoregressive end-to-end architecture, it is more than 5x faster than Whisper-Small and more than 15x faster than Whisper-Large at similar parameter scales.
Key Takeaways
- SenseVoice is a foundational speech understanding model supporting ASR,language…
- The released SenseVoiceSmall checkpoint supports Mandarin,Cantonese,English,Japanese,and Korean…
- using a non-autoregressive end-to-end architecture,it is more than 5x faster than Whisper-Small…
Quick Facts
- Published
- Updated
- Source
- 通义 QwenAudio:原创语音项目
- Category
- Products & Apps
- AI score
- 61
官方仓库文档同时给出基准对比、部署路径和微调方案,读者可以据此评估 SenseVoice 在中英文语音识别场景的可用性。
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: SenseVoice open-source speech understanding model repository supports ASR, emotion recognition, and audio event detection. July 3, 2024. https://new.nat6.net/en/news/cmtyq8s6102v3roup5qwf5ciz/