好网站,从官网开始
企业认领/联系与合作
官网导航 提交官网
F

FunAudioLLM官网

由阿里巴巴集团通义语音团队开发的框架,旨在增强人类与大型语言模型(LLMs)之间的自然语音交互

官网资料

网站名称
FunAudioLLM
身份核实
尚未完成企业认领核实
最近更新
链接检测
尚未检测

关于 FunAudioLLM

FunAudioLLM Homepage FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs [ Paper ] [ Code ] [Modelscope: SenseVoice CosyVoice ] [HuggingFace: SenseVoice CosyVoice] Tongyi SpeechTeam Alibaba Group Abstract: This report introduces FunAudioLLM , a framework designed to enhance natural voice interactions between humans and large language models (LLMs). At its core are two innovative models: SenseVoice for high-precision multilingual speech recognition, emotion recognition, and audio event detection; and CosyVoice for natural speech generation with multi-language, timbre, and emotion control. SenseVoice delivers exceptionally low latency and supports over 50 languages, while CosyVoice excels in multi-lingual voice generation, zero-shot voice generation, cross-lingual voice cloning, and instruction-following capabilities. The models related to SenseVoice and CosyVoice have been open-sourced on Modelscope and Huggingface, along with the corresponding training, inference, and fine-tuning codes released on GitHub. By integrating these models with LLMs, FunAudioLLM enables applications such as speech translation, emotional voice chat, interactive podcasts, and expressive audiobook narration, thereby pushing the boundaries of voice interaction technology. SenseVoice supports high-precision multilingual ASR, excels over Whisper in Chinese and Cantonese recognition, and has SOTA emotion recognition capabilities. SenseVoice-small has extremely high inference efficiency, being 7 times faster than Whisper-small and 17 times faster than Whisper-large. The CosyVoice model, pre-trained on 150,000+ hours of meticulous multi-lingual, multi-speaker data, pioneers as the first industry-grade, open-source speech synthesis tool. CosyVoice offers multi-language support for English, Mandarin, Japanese, Korean, and Cantonese, enabling zero-shot voice generation, and includes seven speakers fine-tuned for immediate use. CosyVoice-instruct also offers emotional expression, event control, and detailed adjustments like speed and pitch, and it ensures versatile and nuanced speech generation. FunAudioLLM has developed a variety of application demos, including simultaneous interpretation, emotional voice interaction, interactive podcasts, and multi-character audiobook narration. --> Contents Applications Speech-to-Speech Translation Emotional VoiceChat Interactive PodCast Expressive Audiobook Voice Generation Model: CosyVoice Ove

访问提示

本站仅提供官网信息与访问导航,不代表对该网站的产品、服务或交易作出担保。访问外部网站时,请核对网址,注意账号和财产安全。

同类型网站 366

查看分类

AutoGPT 是面向自主智能体的开源平台,支持用自然语言或可视化流程创建、运行和管理能够持续执行任务的智能体。

支持多 AI Agent 框架的可视化管理面板,支持 OpenClaw 和 Hermes Agent 双引擎,内置智能助手一键安装诊断

让更多人找到你的官网

提交网站信息,建立清晰、完整的官网资料。

免费提交官网

咨询提交、推广、认领

客服微信二维码,长按识别或保存后使用微信扫一扫

扫一扫添加微信,沟通官网导航提交、认领、推广需求。

可长按识别,或保存图片后在微信扫一扫中识别。

添加时可备注“官网导航”,便于沟通您的企业需求。

保存二维码 打开原图