Automatic Speech Recognition
MLX
Safetensors
PyTorch
English
quantized
speech-recognition
cache-aware ASR
streaming-asr
speech
audio
FastConformer
RNNT
Parakeet
ASR
NeMo
Instructions to use lightsofapollo/nemotron-speech-streaming-en-0.6b-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use lightsofapollo/nemotron-speech-streaming-en-0.6b-8bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir nemotron-speech-streaming-en-0.6b-8bit lightsofapollo/nemotron-speech-streaming-en-0.6b-8bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
Initial upload: 8-bit MLX quantized Nemotron streaming ASR (CC-BY-4.0 derivative of nvidia/nemotron-speech-streaming-en-0.6b)
3b6574b verified - Xet hash:
- e6d9af95b8ed8115677272910ac6f201fae77b925732f00e0f2ead16d941c8c0
- Size of remote file:
- 251 kB
- SHA256:
- 07d4e5a63840a53ab2d4d106d2874768143fb3fbdd47938b3910d2da05bfb0a9
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.