kaldi :详解aishell-1全过程【数据准备】
环境:ubantu18.04
过程简单说来就是:
①语料数据准备 下载语料库到本地/服务器的文件夹
data_url=www.openslr.org/resources/33
. ./cmd.sh
local/download_and_untar.sh $data $data_url data_aishell || exit 1;
local/download_and_untar.sh $data $data_url resource_aishell || exit 1;
②数据关系,词典、语言文件(text, wav.scp, utt2pk, spk2utt)准备,训练集、测试集、验证集准备
#Lexicon Preparation
local/aishell_prepare_dict.sh $data/resource_aishell || exit 1;
#Data Preparation,
local/aishell_data_prep.sh $data/data_aishell/wav $data/data_aishell/transcript || exit 1;
#Phone Sets, questions, L compilation
utils/prepare_lang.sh --position-dependent-phones false data/local/dict \
"<SPOKEN_NOISE>" data/local/lang data/lang || exit 1;
ain_dir=data/local/train
dev_dir=data/local/dev
test_dir=data/local/test
tmp_dir=data/local/tmp
③单音素(或者其他模型)训练和解码
④构建解码图
⑤解码查看


2万+

被折叠的 条评论
为什么被折叠?



