GLM ASR Nano 2512
GLM ASR Nano 2512 is an open-source automatic speech recognition model from zai-org with MIT license and 1.5B parameters. It supports English, Chinese, and Cantonese/dialects, with claimed robustness for low-volume speech and benchmark performance compared to Whisper V3 and other open-source models. It is intended for use with transformers and planned support for vLLM and SGLang.
At a glance
- Parameters
- 2.26B
- Architecture
- glmasr
- License
- mit
- Disk space
- 4.2 GB
- Software
- Transformers, Transformers
Will it run on your machine?
Save your machine to see a personalized rating and its reasoning.
Add my hardwareBest for
- Transcribing English or Mandarin audio
- Transcribing Cantonese or dialectal speech
- Recognizing very quiet or whispered speech
- Processing speech in noisy meeting-like environments
- Batched automatic speech recognition with transformers
Tradeoffs
- Only English, Chinese, and Cantonese/dialect language support are stated; other languages are not confirmed
- Does not include full deployment or framework support beyond transformers in the source
- Performance claims are source-provided and not independently verified here
- No information about hardware requirements, speed, or compatibility beyond the model card
- No license or usage guidance beyond the stated MIT license
Ways to run it
Transformers · See official guide
Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.
from transformers import AutoModelForSeq2SeqLM, AutoProcessor
processor = AutoProcessor.from_pretrained("zai-org/GLM-ASR-Nano-2512")
model = AutoModelForSeq2SeqLM.from_pretrained("zai-org/GLM-ASR-Nano-2512", dtype="auto", device_map="auto")
inputs = processor.apply_transcription_request("https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/bcn_weather.mp3")
inputs = inputs.to(model.device, dtype=model.dtype)
outputs = model.generate(**inputs, do_sample=False, max_new_tokens=500)
decoded_outputs = processor.batch_decode(outputs[:, inputs.input_ids.shape[1] :], skip_special_tokens=True)
print(decoded_outputs)Transformers · See official guide
Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.
from transformers import AutoModel, AutoProcessor
import torch
device = "cuda" if torch.cuda.is_available() else "cpu"
repo_id = "zai-org/GLM-ASR-Nano-2512"
processor = AutoProcessor.from_pretrained(repo_id)
model = AutoModel.from_pretrained(repo_id, dtype=torch.bfloat16, device_map=device)
messages = [
{
"role": "user",
"content": [
{
"type": "audio",
"url": "example_zh.wav",
},
{"type": "text", "text": "Please transcribe this audio into text"},
],
}
]
inputs = processor.apply_chat_template(
messages, tokenize=True, add_generation_prompt=True, return_dict=True, return_tensors="pt"
)
inputs = inputs.to(device, dtype=torch.bfloat16)
outputs = model.generate(**inputs, max_new_tokens=128, do_sample=False)
print(processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True))Explore its uses
Keep exploring
Voxtral Mini · 4B Realtime
Voxtral Mini 4B Realtime 2602 is a multilingual, realtime automatic speech recognition model from Mistral AI, released under the Apache-2.0 license. It features a natively streaming architecture with a causal audio encoder and sliding window attention, enabling configurable transcription delays from 240ms to 2.4s (and reportedly 80ms to 2.4s). The model has approximately 4B parameters (≈3.4B language model and ≈970M audio encoder) and is described as optimized for on-device deployment. It supports 13 languages and is presented as achieving accuracy comparable to offline systems with less than 500ms delay, specifically matching leading offline open-source models and realtime APIs at a 480ms delay. The model card recommends a temperature of 0.0, using websockets for audio streaming, and a delay of 480ms as a balance between performance and latency.
YuE2 · 3B
Create a full song from style and lyrics with a publisher Python package on a Linux NVIDIA GPU; outputs include a playable FLAC.
LFM3-Audio-2B
Liquid AI’s official 2B speech model from the LFM3 family: speech recognition, text-to-speech and spoken chat in one small model that runs on a laptop.