Skip to content
Projects
Groups
Snippets
Help
This project
Loading...
Sign in / Register
Toggle navigation
C
ct-transformer
Overview
Overview
Details
Activity
Cycle Analytics
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Charts
Issues
0
Issues
0
List
Board
Labels
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Charts
Wiki
Wiki
Snippets
Snippets
Members
Collapse sidebar
Close sidebar
Activity
Graph
Charts
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
tongtao.ling
ct-transformer
Commits
5b0712bd
Commit
5b0712bd
authored
Oct 08, 2024
by
tongtao.ling
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
update README.md
parent
eb79f6fc
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
19 additions
and
0 deletions
+19
-0
README.md
+19
-0
No files found.
README.md
View file @
5b0712bd
...
...
@@ -23,3 +23,21 @@ Controllable Time-delay Transformer是达摩院语音团队提出的语音识别
顺滑检测使用csc数据(https://github.com/shibing624/pycorrector/tree/master/examples/data/sighan_2015),生成数据的脚本可见
[
create_dataset.py
](
create_dataset.py
)
,微调代码
[
finetune.py
](
finetune.py
)
标点恢复任务使用iwslt2012_zh数据(https://github.com/jiangnanboy/punctuation_prediction/blob/main/data/iwslt2012_zh.rar)。
## 效果
```
Input: 因为我们也做商标商标申请,商标标呃专利申请啊,所以这这个这特定的专业组开始可能需要需要特定的这个写呃那个一些数据库和系统啊,那这些可能都是软件啊。
Output: 因为我们也做商标申请,商标专利申请,所以这个特定的专业组开始可能需要特定的这个写那个一些数据库和系统,那这些可能都是软件啊。
运行时间(CPU): 17.20
Input: 当当然可能可能刚好就那个呃,他那边对也也也也是我的客户,那我不能代表您去告他,对不对?那对对对对,这就有一冲了,这才是这个概念。
Output: 当然可能刚好就那个,他那边对也是我的客户,那我不能代表您去告他,对不对?那对,这就有一冲了,这才是这个概念。
运行时间(CPU): 7.93 毫秒
```
\ No newline at end of file
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment