From a604f4617106f83958dcd3971b47879f8121c193 Mon Sep 17 00:00:00 2001 From: Fangjun Kuang Date: Mon, 10 Jan 2022 10:55:58 +0800 Subject: [PATCH] Add RESULTS. --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index ff93e8fad..0b47b62ff 100644 --- a/README.md +++ b/README.md @@ -84,12 +84,12 @@ The best WER using beam search with beam size 4 is: | | test-clean | test-other | |-----|------------|------------| -| WER | 2.83 | 7.19 | +| WER | 2.76 | 6.97 | Note: No auxiliary losses are used in the training and no LMs are used in the decoding. -We provide a Colab notebook to run a pre-trained transducer conformer + stateless decoder model: [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1Lm37sNajIpkV4HTzMDF7sn9l0JpfmekN?usp=sharing) +We provide a Colab notebook to run a pre-trained transducer conformer + stateless decoder model: [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1Rc4Is-3Yp9LbcEz_Iy8hfyenyHsyjvqE?usp=sharing) ### Aishell