marcoyang
/

librispeech_bigram

Model card Files Files and versions

librispeech_bigram / README.md

marcoyang's picture

Create README.md

1fc51a0 almost 3 years ago

|

history blame contribute delete

179 Bytes

	This is a token bi-gram trained on LibriSpeech 960h text. It is used for LODR decoding in `icefall`.

	Please refer to https://github.com/k2-fsa/icefall/pull/678 for more details.