You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
PaddleSpeech/text_processing/README.md

26 lines
509 B

This file contains ambiguous Unicode characters!

This file contains ambiguous Unicode characters that may be confused with others in your current locale. If your use case is intentional and legitimate, you can safely ignore this warning. Use the Escape button to highlight these characters.

# PaddleSpeechTask
A speech library to deal with a series of related front-end and back-end tasks
## 环境
- python==3.6.13
- paddle==2.1.1
## 中/英文文本加标点任务 punctuation restoration
### 数据集: data
- 中文数据来源data/chinese
1.iwlst2012zh
2.平凡的世界
- 英文数据来源: data/english
1.iwlst2012en
- iwlst2012数据获取过程见data/README.md
### 模型speechtask/punctuation_restoration/model
1.BLSTM模型
2.BertLinear模型
3.BertBLSTM模型