From c0709c81070650f0f8e27e4803af292826128972 Mon Sep 17 00:00:00 2001 From: marcoyang1998 <45973641+marcoyang1998@users.noreply.github.com> Date: Thu, 29 Jun 2023 12:09:40 +0800 Subject: [PATCH] Update docs/source/decoding-with-langugage-models/LODR.rst Co-authored-by: Fangjun Kuang --- docs/source/decoding-with-langugage-models/LODR.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/source/decoding-with-langugage-models/LODR.rst b/docs/source/decoding-with-langugage-models/LODR.rst index 1d8562843..160fca353 100644 --- a/docs/source/decoding-with-langugage-models/LODR.rst +++ b/docs/source/decoding-with-langugage-models/LODR.rst @@ -161,7 +161,7 @@ The decoding results obtained with the above command are shown below: $ For test-other, WER of different settings are: $ beam_size_4 6.74 best for test-other -Recall that the lowest WER we obtained in :ref:`shallow_fusion` with beam size of 4 is 2.77/7.08, LODR +Recall that the lowest WER we obtained in :ref:`shallow_fusion` with beam size of 4 is ``2.77/7.08``, LODR indeed **further improves** the WER. We can do even better if we increase ``--beam-size``: .. list-table:: WER of LODR with different beam sizes