Update docs/source/decoding-with-langugage-models/LODR.rst

Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>
This commit is contained in:
marcoyang1998 2023-06-29 12:10:28 +08:00 committed by GitHub
parent e429a152e9
commit 2f1af8f303
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -148,7 +148,7 @@ Then, we perform LODR decoding by setting ``--decoding-method`` to ``modified_be
--tokens-ngram 2 \ --tokens-ngram 2 \
--ngram-lm-scale $LODR_scale --ngram-lm-scale $LODR_scale
There are two extra arguments need to be given when doing LODR. ``--tokens-ngram`` specifies the order of n-gram. As we There are two extra arguments that need to be given when doing LODR. ``--tokens-ngram`` specifies the order of n-gram. As we
are using a bi-gram, we set it to 2. ``--ngram-lm-scale`` is the scale of the bi-gram, it should be a negative number are using a bi-gram, we set it to 2. ``--ngram-lm-scale`` is the scale of the bi-gram, it should be a negative number
as we are subtracting the bi-gram's score during decoding. as we are subtracting the bi-gram's score during decoding.