%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
Zhipu AI has officially launched its latest GLM-ASR series speech recognition model and open-sourced the related technology, aiming to provide users with a more efficient voice interaction experience. The launch of this series also includes a desktop "Zhipu AI Input Method," offering great convenience for voice input on PC platforms.
GLM-ASR-2512 is Zhipu AI's globally leading cloud-based speech recognition model. Its main feature is real-time speech-to-text conversion, performing excellently in complex real-world environments, with a character error rate (CER) as low as 0.0717. This outstanding recognition accuracy keeps it at the forefront of the industry in multi-scenario, multi-language, and multi-accent applications.
In addition to GLM-ASR-2512, Zhipu AI has also open-sourced GLM-ASR-Nano-2512. This model has only 1.5B parameters but performs SOTA in the open-source speech recognition field, even surpassing some closed-source models in certain tests. The design of GLM-ASR-Nano-2512 allows it to run locally, ensuring high-precision speech recognition while enhancing user privacy and reducing interaction latency.
Based on the powerful capabilities of these two models, Zhipu AI has launched the new Zhipu AI Input Method. Users can not only achieve accurate speech-to-text functionality through this input method but also perform intelligent operations such as translation and text rewriting, truly realizing the convenient experience of "指尖即模型，语音即指令" (the fingertip is the model, and voice is the command). Currently, the Zhipu AI Input Method is available to all users, and new users can get 2000 points, enjoying up to 28 days of free usage time.
GLM-ASR-Nano-2512: Hugging Face: https://huggingface.co/zai-org/GLM-ASR-Nano-2512
Zhipu AI Input Method: https://autoglm.zhipuai.cn/autotyper/
Key Points:
🌟 Launch of the GLM-ASR series model, including a globally leading cloud-based speech recognition model and an edge-side model, with excellent recognition accuracy.
🛠️ Launch of the new Zhipu AI Input Method, supporting speech-to-text, translation, and rewriting, providing a convenient PC-based voice interaction experience.
🎁 New users can get 2000 points for free, enjoying up to 28 days of usage, encouraging more users to experience the smart input method.