GGitHubRevert "[engine] merge develop into speechx (#3198 )" (#3199 )

500f283d创建于 2023年4月24日历史提交

文件	最后提交记录	最后更新时间
data	Update textnorm_test_cases.txt	3 年前
README.md	Added pre-install doc for G2P and TN modules and updated the dependency version of pypinyin (#2364) * Added pre-install doc for G2P and TN modules and updated the dependency version of pypinyin, test=doc	3 年前
get_textnorm_data.py	change nprocs to ngpu, add aishell3/voc1	4 年前
path.sh	[TTS]fix praatio version, test=tts (#1158) * fix praatio version, test=tts * fix praatio version, test=tts	4 年前
run.sh	change nprocs to ngpu, add aishell3/voc1	4 年前
test_textnorm.py	change nprocs to ngpu, add aishell3/voc1	4 年前

Text Normalization

For text normalization, the test data is data/textnorm_test_cases.txt, we use | as the separator of raw_data and normed_data.

We use CER as an evaluation criterion.

Start

Run the command below to get the results of the test.

cd ../../../tools
bash extras/install_sclite.sh
cd -
./run.sh

The avg CER of text normalization is: 0.00730093543235227

      ,-----------------------------------------------------------------.
      |        | # Snt  # Wrd | Corr    Sub    Del    Ins    Err  S.Err |
      |--------+--------------+-----------------------------------------|
      | Sum/Avg|  125    2254 | 99.4    0.1    0.5    0.2    0.8    4.8 |
      `-----------------------------------------------------------------'