-
Notifications
You must be signed in to change notification settings - Fork 3k
Insights: 2noise/ChatTTS
Overview
There hasn’t been any commit activity on 2noise/ChatTTS in the last week.
Want to help out?
12 Pull requests merged by 2 people
-
chore(format): run black on dev
#597 merged
Jul 19, 2024 -
chore(format): run black on dev
#594 merged
Jul 19, 2024 -
chore(format): run black on dev
#592 merged
Jul 18, 2024 -
chore(format): run black on dev
#591 merged
Jul 18, 2024 -
chore(format): run black on dev
#590 merged
Jul 18, 2024 -
chore(format): run black on dev
#589 merged
Jul 18, 2024 -
chore(env): sync checksum on dev
#584 merged
Jul 18, 2024 -
chore(format): run black on dev
#583 merged
Jul 18, 2024 -
fix stream mode, last chunk of audio file size
#564 merged
Jul 16, 2024 -
chore(env): sync checksum on dev
#575 merged
Jul 16, 2024 -
chore(env): sync checksum on dev
#574 merged
Jul 16, 2024 -
chore(format): run black on dev
#573 merged
Jul 16, 2024
1 Pull request opened by 1 person
-
chore(format): run black on dev
#598 opened
Jul 19, 2024
77 Issues closed by 4 people
-
TELlamaModel问题
#596 closed
Jul 19, 2024 -
我调用了很多次，发现每次调用的角色声音可能不一样。
#15 closed
Jul 19, 2024 -
关于高频音
#192 closed
Jul 19, 2024 -
这个能同时生成音素吗，方便口型的开发
#193 closed
Jul 19, 2024 -
长文本请教
#197 closed
Jul 19, 2024 -
可以这样保存音色
#203 closed
Jul 19, 2024 -
paper or technical notes
#209 closed
Jul 19, 2024 -
出现未定义字符后 语气推导的text的 tag 会丢失[]
#424 closed
Jul 18, 2024 -
流式输出的音频有噪音
#521 closed
Jul 18, 2024 -
流式推理的时候24个code解码一次，不同的分段之间没有瑕疵，训练时做了特殊处理吗？
#585 closed
Jul 18, 2024 -
最后一个单词发音不完整
#576 closed
Jul 18, 2024 -
一个windows配置过程
#73 closed
Jul 18, 2024 -
Windows环境下显示Windows not yet supported for torch.compile，而WSL环境下性能不佳，4090下只能以40s/it的速度生成
#112 closed
Jul 18, 2024 -
执行完无任何输出
#132 closed
Jul 18, 2024 -
ModuleNotFoundError: No module named '_pynini'，请教用win10运行的大佬们，没有更改pynini任何东西，为啥报这个错？
#147 closed
Jul 18, 2024 -
文字多的情况下会漏读
#166 closed
Jul 18, 2024 -
Driver c++ error fixing
#174 closed
Jul 18, 2024 -
请问如何���升输出语音长度
#185 closed
Jul 18, 2024 -
启动运行报错 ，下载安装是提示：客户端没有执行权限，然后dvae.yaml缺少了
#189 closed
Jul 18, 2024 -
How to save output to a wav or mp3?
#41 closed
Jul 17, 2024 -
如何切换女生音色呢
#97 closed
Jul 17, 2024 -
在服务器部署后，推理速度比较慢，GPU没有吃满，吃满了一个CPU核心
#103 closed
Jul 17, 2024 -
modelscope中缺少 spk_stat.pt
#107 closed
Jul 17, 2024 -
请问README里的两段话是用这个开源的版本做的吗?
#119 closed
Jul 17, 2024 -
阅读英文单词回出现混乱的情况
#120 closed
Jul 17, 2024 -
Load Model这一步报错UnpicklingError: invalid load key, 'v'
#122 closed
Jul 17, 2024 -
未找到文件 [Errno 2] No such file or directory:
#127 closed
Jul 17, 2024 -
安装依赖报错
#130 closed
Jul 17, 2024 -
NameError: name 'chat' is not defined
#131 closed
Jul 17, 2024 -
有些字念错了
#134 closed
Jul 17, 2024 -
文字多了会乱套
#135 closed
Jul 17, 2024 -
web_ui refine text的插入表情下划线是中文标点符号： ［uv＿break］
#151 closed
Jul 17, 2024 -
No module named 'tokenizers'
#566 closed
Jul 16, 2024 -
程序在M1芯片上跑到8%-10%左右就终止，无错误提示
#24 closed
Jul 16, 2024 -
Any plan to release fine tuning with your own voice?
#27 closed
Jul 16, 2024 -
TypeError: LlamaModel.forward() got an unexpected keyword argument 'cache_position'
#28 closed
Jul 16, 2024 -
根据音色种子设定音色的标准方法的疑问
#63 closed
Jul 16, 2024 -
demo code running error
#68 closed
Jul 16, 2024 -
为什么生成的音频有很大的噪声
#79 closed
Jul 16, 2024 -
怎么调整成女生音色?
#80 closed
Jul 16, 2024 -
某些词似乎不能够发音
#81 closed
Jul 16, 2024 -
ChatTTs 需要的环境我基本都弄好了，但是运行起来还是报错，有大神能帮我解惑吗？
#82 closed
Jul 16, 2024 -
Multiple language errors
#85 closed
Jul 16, 2024 -
希望项目内置一个基于项目底模用来训练模型的.py文件
#94 closed
Jul 16, 2024 -
如何将运行的wav保存下来呢？
#95 closed
Jul 16, 2024 -
win11无法调用gpu
#99 closed
Jul 16, 2024 -
加载权重文件报错：AssertionError
#105 closed
Jul 16, 2024 -
如何正确读链接？
#114 closed
Jul 16, 2024 -
短句貌似没法转出语音
#116 closed
Jul 16, 2024 -
Can ChatTTS clone voice?
#124 closed
Jul 16, 2024 -
你好，体验了一下非常棒，咱们计划什么时候发布流式输出的版本，当前版本是否能支持多GPU加速生成？
#125 closed
Jul 16, 2024 -
有偿合作
#569 closed
Jul 15, 2024 -
webui保存音色，使用固定音色推理
#152 closed
Jul 15, 2024 -
Ubuntu 上执行webui.py 遇到 libcuda.so 找不到的问题及其解决方案
#213 closed
Jul 15, 2024 -
创建了一个汇总安装指南、参数说明、音色列表、常见问题、资源推荐的入门指南，新人建议先完整看一遍
#277 closed
Jul 15, 2024 -
I built a research article to podcast generation with ChatTTS
#295 closed
Jul 15, 2024 -
decoder.yaml sha256 hash mismatch
#567 closed
Jul 15, 2024 -
怎么使用啊大佬，纯小白
#7 closed
Jul 15, 2024 -
where should i place pretrain models？
#20 closed
Jul 15, 2024 -
这几个参数的取值范围以及意义是什么呢？
#45 closed
Jul 15, 2024 -
生成音频了，但是有几个小问题
#48 closed
Jul 15, 2024 -
文本里面的阿拉伯数字好像识别不了
#50 closed
Jul 15, 2024 -
ASR任务
#52 closed
Jul 15, 2024 -
怎样支持西班牙语呢?
#53 closed
Jul 15, 2024 -
提供一个poetry环境配置
#54 closed
Jul 15, 2024 -
import ChatTTS出错
#55 closed
Jul 15, 2024 -
audio[]括号中的数字代表什么？报错list index out of range
#56 closed
Jul 15, 2024 -
想请问一下为什么有时候会多说一两个字，无法用在正式新闻类播报场景。
#58 closed
Jul 15, 2024 -
add model to hugging face
#64 closed
Jul 15, 2024 -
Please add refining text option configuration for reading novels
#65 closed
Jul 15, 2024 -
有相关论文吗，后续有开源训练代码的计划吗
#11 closed
Jul 14, 2024 -
How to generate speaker?
#13 closed
Jul 14, 2024 -
About vq selection
#17 closed
Jul 14, 2024 -
请问用的是什么 tokenizer 呢？
#4 closed
Jul 13, 2024
15 Issues opened by 14 people
-
安装 flash-attn 可选项的时候报错
#595 opened
Jul 19, 2024 -
api推理第一次加载完模型之后，生成输出文本和音频时间需要5分钟，太慢。
#593 opened
Jul 18, 2024 -
最新版多句推理时，refine_text问题
#588 opened
Jul 18, 2024 -
请问使用webui进行流式推理的时候音频播放为什么会有5秒钟左右的延迟？
#587 opened
Jul 18, 2024 -
chattts可以在cuda 11.8环境下运行吗？
#586 opened
Jul 18, 2024 -
输入的text和生成的text有变化。不仅添加了停��和语气词，还添加了没必要的文字。这个怎么设置？
#582 opened
Jul 18, 2024 -
怎么取消掉文本优化？？？？！！！
#581 opened
Jul 18, 2024 -
[uv_break]会被直接读出来
#580 opened
Jul 18, 2024 -
AttributeError: 'TELlamaDecoderLayer' object has no attribute 'mlp'
#579 opened
Jul 18, 2024 -
文本框里的内容可以批量更新吗
#578 opened
Jul 17, 2024 -
开源协议 AGPL-v3.0
#577 opened
Jul 17, 2024 -
TypeError: 'RefineTextParams' object is not subscriptable
#572 opened
Jul 16, 2024 -
'Chat' object has no attribute 'load_models'
#571 opened
Jul 15, 2024 -
自定义模型目录报错
#570 opened
Jul 14, 2024 -
AttributeError: 'Chat' object has no attribute 'gpt'如何决解
#565 opened
Jul 12, 2024
17 Unresolved conversations
Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.
-
what is the set up/install to be used to test and install this in google colab?
#268 commented on
Jul 13, 2024 • 0 new comments -
技术原理
#313 commented on
Jul 14, 2024 • 0 new comments -
Error installing and running on apple silicon - M1 chip
#263 commented on
Jul 14, 2024 • 0 new comments -
训练数据是怎么标注的？能不能放些样例出来
#308 commented on
Jul 15, 2024 • 0 new comments -
是否可以支持ollama
#297 commented on
Jul 15, 2024 • 0 new comments -
找到一种固定音色的方法
#123 commented on
Jul 15, 2024 • 0 new comments -
License
#318 commented on
Jul 15, 2024 • 0 new comments -
绕口令的生成效果不佳|Tongue twister generation is not good
#322 commented on
Jul 16, 2024 • 0 new comments -
请问支持音色克隆吗
#319 commented on
Jul 16, 2024 • 0 new comments -
unexpected keyword argument 'compile'
#326 commented on
Jul 17, 2024 • 0 new comments -
how to use?
#42 commented on
Jul 17, 2024 • 0 new comments -
What is the difference between [lbreak] and [uv_break]?
#330 commented on
Jul 17, 2024 • 0 new comments -
生成语音质量不错，但速度太慢 没法用
#265 commented on
Jul 18, 2024 • 0 new comments -
最新版本Windows跑不起来的处理办法。
#168 commented on
Jul 18, 2024 • 0 new comments -
OSError: [WinError 126] 找不到指定的模块。 Error loading
#156 commented on
Jul 18, 2024 • 0 new comments -
TypeError: load_models() got an unexpected keyword argument 'sourc
#142 commented on
Jul 18, 2024 • 0 new comments