From b96bd6490c3ac20378f0923a9dca4aa5b0a371f7 Mon Sep 17 00:00:00 2001 From: Mingshuang Luo <37799481+luomingshuang@users.noreply.github.com> Date: Sat, 9 Oct 2021 10:15:20 +0800 Subject: [PATCH] Update conformer_ctc.rst --- docs/source/recipes/librispeech/conformer_ctc.rst | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) diff --git a/docs/source/recipes/librispeech/conformer_ctc.rst b/docs/source/recipes/librispeech/conformer_ctc.rst index 735e6376a..73c5503d8 100644 --- a/docs/source/recipes/librispeech/conformer_ctc.rst +++ b/docs/source/recipes/librispeech/conformer_ctc.rst @@ -292,16 +292,16 @@ The commonly used options are: - ``--method`` - This specifies the decoding method. This script support seven decoding methods. + This specifies the decoding method. This script supports 7 decoding methods. As for ctc decoding, it uses a sentence piece model to convert word pieces to words. And it needs neither a lexicon nor an n-gram LM. - For example, the following command uses CTC topology for rescoring: + For example, the following command uses CTC topology for decoding: .. code-block:: $ cd egs/librispeech/ASR - $ ./conformer_ctc/decode.py --method ctc-decoding --max-duration 300 --bucketing-sampler False + $ ./conformer_ctc/decode.py --method ctc-decoding --max-duration 300 And the following command uses attention decoder for rescoring: @@ -319,12 +319,8 @@ The commonly used options are: It has the same meaning as the one during training. A larger value may cause OOM. - - - ``--bucketing-sampler`` - When enabled, the batches will come from buckets of similar duration (saves padding frames). - -Here are some results for reference based on CTC decoding when set vocab size as 500: +Here are some results for CTC decoding with a vocab size of 500: Usage: @@ -335,8 +331,6 @@ Usage: --epoch 25 \ --avg 1 \ --max-duration 300 \ - --bucketing-sampler 0 \ - --full-libri 0 \ --exp-dir conformer_ctc/exp \ --lang-dir data/lang_bpe_500 \ --method ctc-decoding