Instructions to use pltobing/nemo-asr-cache-aware-streaming-160ms-en-onnx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use pltobing/nemo-asr-cache-aware-streaming-160ms-en-onnx with NeMo:
# tag did not correspond to a valid NeMo domain.
- Notebooks
- Google Colab
- Kaggle
metadata
language:
- en
tags:
- nemo
- onnx
- asr
- streaming
- cache-aware
- conformer-rnnt
license: apache-2.0
base_model: nvidia/nemotron-speech-streaming-en-0.6b
ONNX cache-aware streaming ASR Nemo (Conformer-RNNT) [EN-0.16s]
Device: CPU
Language: English
Latency: 160ms (1 + 1 future context chunks; 1 chunk is 8 frames; 1 frame is 10ms)
Model origin: https://huggingface.co/nvidia/nemotron-speech-streaming-en-0.6b
ONNX origin: https://github.com/istupakov/onnx-asr