GLM-ASR-Nano-2512 is a small-scale automatic speech recognition model based on the GLM architecture. It supports audio input processing and includes a specialized chat template for handling conversational speech-to-text tasks. The model is hosted on Hugging Face and is intended for integration into applications via the Transformers library or compatible inference providers.
GLM ASR Nano 2512 is a Voice, TTS & speech project. It focuses on converting spoken audio into text using a lightweight neural model. It is built as an open-source project for developers. The project is open source (Apache-2.0). GLM ASR Nano 2512 is available on the web, the command line, and API.
It is developed by zai-org, and it first shipped in 2025. Development happens publicly on GitHub with 833 stars.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match