GLM-ASR-Nano-2512语音识别模型有支持计划吗？ #4616
Description
Feature request / 功能建议
增加GLM-ASR-Nano-2512语音识别模型
Motivation / 动机
GLM-ASR-Nano-2512 is a robust, open-source speech recognition model with 1.5B parameters (2B model size). Designed for real-world complexity, it outperforms OpenAI Whisper V3 on multiple benchmarks while maintaining a compact size.
Key Capabilities
Exceptional Dialect Support: Beyond standard Mandarin and English, the model is highly optimized for Cantonese (粤语) and other dialects, effectively bridging the gap in dialectal speech recognition.
Low-Volume Speech Robustness: Specifically trained for "Whisper/Quiet Speech" scenarios. It captures and accurately transcribes extremely low-volume audio that traditional models often miss.
SOTA Performance: Achieves the lowest average error rate (4.10) among comparable open-source models, showing significant advantages in Chinese benchmarks (Wenet Meeting, Aishell-1, etc.).
Your contribution / 您的贡献
GLM-ASR Usage Guide https://github.com/vllm-project/recipes/blob/main/GLM/GLM-ASR.md