add tokenizer config.

pull/3023/head
zxcd 3 years ago
parent 175db0682d
commit 1a196e0ad0

@ -107,6 +107,7 @@ vocab_filepath: data/lang_char/vocab.txt
###########################################
unit_type: 'char'
tokenizer: bert-base-chinese
mean_std_filepath:
preprocess_config: conf/preprocess.yaml
sortagrad: -1 # Feed samples from shortest to longest ; -1: enabled for all epochs, 0: disabled, other: enabled for 'other' epochs

Loading…
Cancel
Save