GLM-ASR-Nano-2512

About

What GLM-ASR-Nano-2512 is

GLM-ASR-Nano-2512 👋 Join our <a href="https://raw.githubusercontent.com/zai-org/GLM-ASR/refs/heads/main/resources/wechat.png" target="blank"WeChat</a community Model Introduction 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. Key capabilities include: 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..). Benchmark We evaluated GLM-ASR-Nano against leading open-source and closed-source models. The results demonstrate that GLM-ASR-Nano (1.5B) achieves superior performance, particularly in challenging acoustic environments. Notes: - Wenet Meeting reflects real-world meeting scenarios with noise and overlapping speech. - Aishell-1 is a standard Mandarin benchmark. Inference GLM-ASR-Nano-2512 can be easily integrated using the transformers library. We will support transformers 5.x as well as inference frameworks such as vLLM and SGLang. you can check more code in Github. Transformers 🤗 Install transformers from source: Basic Usage Using Audio Arrays Directly You can also use audio arrays directly: Batched Inference You can process multiple audio files at once:

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

How it works

How audio & music work

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys glm-asr-nano-2512 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (glm-asr-nano-2512 below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -F model="glm-asr-nano-2512" -F file=@audio.mp3

Details

Languages, data & research

Licence

Open weights

Sources

Weights & code

Explore

More audio & music