Audar-ASR-V1：首个开源阿拉伯语语音识别基础模型
1 分•作者: AudarAI•3 个月前
大家好，
我们发布了 Audar-ASR-V1，这是 AudarAI 的首次公开版本。
AudarAI 致力于构建多语言音频智能，首期专注于阿拉伯语及其多种方言的语音识别。
我们从阿拉伯语入手，并非因为它是我们的终点，而是因为我们相信在此领域能产生最大的影响力。之后，我们将继续扩展，为全球提供多语言音频智能。
本次发布包含：
* Flash 和 Turbo 开源模型
* 技术报告
* 评估工具
* GitHub 仓库
* 在线演示
我们非常期待研究人员和开发者的反馈。如果您发现问题、有任何建议，或者希望与您的系统进行基准测试，我们都非常乐意听取您的意见。
博客：
https://www.audarai.com/news/introducing-audar-asr-v1
GitHub：
https://github.com/AudarAI/Audar-ASR-V1
Hugging Face：
https://huggingface.co/audarai
查看原文
Hi everyone,
We're releasing Audar-ASR-V1, the first public release from AudarAI.<p>AudarAI is building multilingual audio intelligence, beginning with speech recognition for Arabic and its many dialects.<p>We start with Arabic—not because it is our destination, but because it is where we believe we can make the greatest impact. From there, we continue expanding toward multilingual audio intelligence for the world.<p>This release includes:
• Flash & Turbo open-weight models
• Technical report
• Evaluation harness
• GitHub repository
• Online demos<p>We'd really appreciate feedback from researchers and developers. If you find issues, have suggestions, or want to benchmark against your own systems, we'd love to hear from you.<p>Blog
https://www.audarai.com/news/introducing-audar-asr-v1<p>GitHub
https://github.com/AudarAI/Audar-ASR-V1<p>Hugging Face
https://huggingface.co/audarai