---
license: apache-2.0
---
# Speech recognition with Next-gen Kaldi

This repo contains [ncnn][ncnn] model files, which are converted from
models trained using <https://github.com/k2-fsa/icefall/pull/558>
via [pnnx][pnnx].

The torchscript model is from
<https://huggingface.co/csukuangfj/icefall-asr-librispeech-lstm-transducer-stateless2-2022-09-03>

The inference framework is <https://github.com/k2-fsa/sherpa-ncnn>

# Usage

please see
https://k2-fsa.github.io/sherpa/ncnn/pretrained_models/lstm-transducer-models.html#csukuangfj-sherpa-ncnn-2022-09-05-english
for usage.


[pnnx]: https://github.com/Tencent/ncnn/tree/master/tools/pnnx
[ncnn]: https://github.com/tencent/ncnn