Audio / zai-org

GLM ASR Nano 2512

GLM ASR Nano 2512 from zai-org. Source-based hardware guidance from its published configuration.

EstimatedRepository opened Dec 9, 2025Source checked 9/25/2026Version: 61ba4e0b
LOCALRENTED GPUOPEN WEIGHTS

At a glance

Parameters
2.26B
Architecture
glmasr
License
mit
Disk space
4.2 GB
Software
Transformers, Transformers
View the model source
MY HARDWARE

Will it run on your machine?

Save your machine to see a personalized rating and its reasoning.

Add my hardware

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)
Official instructions

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))
Official instructions

Explore its uses

SAFETENSORS

Keep exploring

Audio
Mistral AI

Voxtral Mini · 4B Realtime

Open-weight, multilingual speech transcription with an official streaming vLLM path and an offline-file Transformers example.

MODEL SIZE4B
Audio
openai

whisper small

whisper-small is a Transformer-based encoder-decoder model for automatic speech recognition and speech translation, from the openai/whisper-small repository, licensed Apache-2.0. According to the supplied model card, it was trained on 680k hours of labelled speech data using large-scale weak supervision and is intended to generalize across datasets and domains without fine-tuning. It is described as trained on either English-only or multilingual data. The model card lists many languages and reports WER metrics for a few dataset/language configurations.

MODEL SIZE0.24B
Audio
openai

whisper tiny

Whisper tiny is an Apache-2.0 licensed OpenAI automatic speech recognition model on the Hugging Face Hub, with safetensors tags. It is a Transformer-based encoder-decoder (sequence-to-sequence) model trained on 680k hours of labelled speech data using large-scale weak supervision. The model card describes training on either English-only or multilingual data; the multilingual variants were trained on both speech recognition and speech translation. Reported metrics on this model card include Test WER 7.54 on LibriSpeech clean, 17.15 on LibriSpeech other, and 141 on Common Voice 11.0 (hi), with multilingual coverage listed for many languages. The model card describes generalisation to many datasets and domains without fine-tuning, but does not specify hardware requirements in the supplied facts.

MODEL SIZE0.04B