zai-org / GLM-ASR-Nano-2512

Audio2.3B27.5K388Updated Apr 7, 2026

Downloads

27.5K

Likes

388

Last updated

Apr 7, 2026

License

mit

GLM-ASR-Nano-2512 is a robust, open-source speech recognition model with 1.5B parameters. Designed for real-world complexity, it outperforms OpenAI Whisper V3 on multiple benchmarks while maintaining a compact size.

Tasks & library

  • automatic speech recognition
  • transformers

Tags

  • transformers
  • glmasr
  • text2text-generation
  • en
  • zh

Technical specifications

Parameters2.3B
Librarytransformers
Languagesen, zh
Licensemit