Automatic Speech Recognition
Safetensors
MLX
English
Chinese
mlx-audio
glmasr
speech-to-text
speech-to-speech
speech
speech generation
stt
custom_code
5-bit
Instructions to use mlx-community/GLM-ASR-Nano-2512-5bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/GLM-ASR-Nano-2512-5bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir GLM-ASR-Nano-2512-5bit mlx-community/GLM-ASR-Nano-2512-5bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
mlx-community/GLM-ASR-Nano-2512-5bit
This model was converted to MLX format from zai-org/GLM-ASR-Nano-2512 using mlx-audio version 0.2.9.
Refer to the original model card for more details on the model.
Use with mlx-audio
pip install -U mlx-audio
CLI Example:
python -m mlx_audio.stt.generate --model mlx-community/GLM-ASR-Nano-2512-5bit--audio "audio.wav"
Python Example:
from mlx_audio.stt.utils import load_model
from mlx_audio.stt.generate import generate_transcription
model = load_model("mlx-community/GLM-ASR-Nano-2512-5bit")
transcription = generate_transcription(
model=model,
audio_path="path_to_audio.wav",
output_path="path_to_output.txt",
format="txt",
verbose=True,
)
print(transcription.text)
- Downloads last month
- 21
Model size
0.4B params
Tensor type
BF16
·
U32 ·
Hardware compatibility
Log In to add your hardware
5-bit