-
- [ ] Believe it or not, you should remove the length checking. Jieba is fast enough for tg's max msg length.
- [ ] Replace all english punctations in zh context with regexes.
- [x] Consider ignoring …
-
Hi, I have already got pyexecjs {Requirement already satisfied: pyexecjs in ./Library/Python/3.7/lib/python/site-packages (1.5.1)} and jieba, but still return this error, could you help with this issu…
-
In function `_g2p_v2`(in `chinese_mix.cpp`)，in order to add `pre_merge_for_modify` (to regulate the Chinese segmentation results), it is necessary to add a sliding window after the Jieba word segmenta…
-
Why does the KeyError occurs?I can not understand.
Can you help me?Thank you
 and [cang-jie](https://crates.io/crates/ca…
-
I am trying to split a chinese text but in the first sentence "我六岁那年看过一本书" , jieba.cut gives me :
["我", "六岁", "那年", "看过", "一", "本书"]
what I am expecting is :
["我", "六", "岁", "那年", "看过", "一", "本"…
-
作者你好, 我要在毕业论文中使用jieba, 有引用的格式吗?
像pkuseg提供了如下格式
```
@inproceedings{DBLP:conf/acl/SunWL12,
author = {Xu Sun and Houfeng Wang and Wenjie Li},
title = {Fast Online Training with Frequency-Adaptive …
-
I am using voice2json as a voice command recognition backend in my [voice interaction mod for a video game](https://github.com/YihaoPeng/DragonbornSpeaksNaturally/releases). As a native Chinese speake…
-
## General Question
我的示例：
paddlespeech_server start --config_file ./conf/tts_online_ws_application.yaml
结果如下：
```
[2023-11-11 09:01:37,518] [ INFO] - endpoint: http://127.0.0.1:8190/paddlesp…
-
GPT-SoVITS 语音总是使用的默认的模型
验证模型：
GPT-SoVITS-v2-240821>runtime\python.exe webui.py zh_CN 语音推理正常
Number of parameter: 77.61M
Number of parameter: 77.61M
实际输入的参考文本: 你好我是娜酱，来自绝区零，是一个游戏角色，欢迎来到未来世界。
…