netease-youdao/EmotiVoice issues and pull requests

#163 - 在WSL下启动API时报OSError

Issue - State: open - Opened by mengz1980 16 days ago

#162 - 影视解说是哪个id

Issue - State: open - Opened by aojh111 about 1 month ago

#161 - OSError: You seem to have cloned a repository without having git-lfs installed. Please install git-lfs and run `git lfs install` followed by `git lfs pull` in the folder you cloned.

Issue - State: open - Opened by 2776721779 about 1 month ago

#160 - 没有体现GPU的优势

Issue - State: open - Opened by manbill about 1 month ago - 1 comment

#159 - 支持onnx推理吗

Issue - State: open - Opened by pengpengtao about 2 months ago

#158 - Missing hardware requirements (GPU Memory)

Issue - State: open - Opened by meng2468 about 2 months ago

#157 - 数字发音不正常

Issue - State: open - Opened by mclkyo 2 months ago

#156 - Create gui.py

Pull Request - State: closed - Opened by john9405 2 months ago

#155 - Any plans to support onnx?

Issue - State: open - Opened by wjddd 3 months ago

#154 - custom voice ? like someone sample audio wave ?

Issue - State: open - Opened by xalteropsx 3 months ago

#153 - 请问对于提示的风格编码器Style Encoder可以使用什么数据进行训练

Issue - State: open - Opened by none-enon 4 months ago

#152 - 结合对话上下文给出符合人类理解的带情绪的回复

Issue - State: open - Opened by Sunwc0 4 months ago

#151 - 报错RuntimeError: CUDA error，

Issue - State: open - Opened by lonngxiang 4 months ago

#150 - 试了里面中文名字的语音，女：4519、6865、7143，男：7556、964这几个尚且能用

Issue - State: open - Opened by leeeex 4 months ago - 3 comments

#149 - 求助！mfa执行第6步报错，老板等着要demo，求救求救

Issue - State: open - Opened by topsoft-support 5 months ago - 1 comment

#148 - 请问这个参数gta = False指的是什么？有什么作用吗

Issue - State: open - Opened by open-eyeslee 5 months ago

#147 - webdemo里面怎么标记多音字

Issue - State: open - Opened by 871052165 5 months ago

#146 - Noised data for Finetune

Issue - State: open - Opened by yadinbenyamin 5 months ago

#145 - Is dialect-languages-finetuning possible on EmotiVoice?

Issue - State: open - Opened by samir1224 6 months ago

#144 - 'sp' can not control pause as expected.

Issue - State: open - Opened by SaltedSlark 6 months ago

#143 - API接口如何处理多音字比如”还（hai2）不还（huan2）钱“

Issue - State: open - Opened by Oceannew 6 months ago - 2 comments

#142 - 请问一下，新增语音情感，StyleEncoder 模型需要重训练吗？怎么训练这个模型呢？

Issue - State: open - Opened by wildBigPanda 6 months ago - 2 comments

#141 - 推理时，生成的音频最后一个字或者最后一个音几乎听不到

Issue - State: closed - Opened by Lili-q 6 months ago - 1 comment

#140 - 请问推理时的sp0，sp1是什么作用，最大的sp是多少？

Issue - State: open - Opened by Jacoo520 6 months ago - 1 comment

#139 - 一次推理的句子最大长度是多少呢？

Issue - State: open - Opened by aidway 6 months ago - 1 comment

#138 - 使用命令行推理报错，张量维度不一致

Issue - State: closed - Opened by aidway 6 months ago - 1 comment

#137 - 能够使用小样本英文进行微调吗？

Issue - State: open - Opened by aidway 6 months ago - 1 comment

#136 - 用自己的数据制定音色

Issue - State: open - Opened by llhzs 7 months ago

#135 - 如何在句子中插入停顿？

Issue - State: open - Opened by Leonard-Li777 7 months ago - 1 comment

#134 - CorpusError

Issue - State: closed - Opened by 1044690543 7 months ago - 2 comments

#133 - 运行网页生成语音没有问题，运行api命令的时候，报了一个No module named 'torch'

Issue - State: open - Opened by qq8344310 7 months ago

#132 - Roadmap for 2024?

Issue - State: open - Opened by tianlinzx 7 months ago

#131 - tts 接口设计不合理

Issue - State: open - Opened by tpoisonooo 7 months ago - 1 comment

#130 - 运行python download.py无效

Issue - State: open - Opened by shangquxiahui 7 months ago

#129 - 找不到demo_page.py文件

Issue - State: closed - Opened by shangquxiahui 7 months ago

#128 - 请问如何在预训练模型克隆多个声音？

Issue - State: open - Opened by liyuhui 8 months ago

#127 - Add a field to adjust the volume

Pull Request - State: closed - Opened by john9405 8 months ago

#126 - how to turn up the volumn from api?

Issue - State: open - Opened by oraclechina 8 months ago

#125 - I only have about twenty wav original files, is it possible clone my original voice by so small samples?

Issue - State: open - Opened by lkyuier 8 months ago

#124 - Which voices are used in the readme?

Issue - State: open - Opened by yakagami 8 months ago

#123 - Add model weights to Hugging Face Hub!

Issue - State: open - Opened by Vaibhavs10 8 months ago

#122 - 没有生成data/xxx/mfa/TextGrid 文件夹

Issue - State: open - Opened by todochenxi 8 months ago - 1 comment

#121 - Style seems not work with web interface ?

Issue - State: open - Opened by acinmavi 8 months ago

#120 - 克隆的模型，训练10万次后，影响已有的声音，下面的8041声音的前后对比，该如何消除影响呢

Issue - State: open - Opened by zebraline 8 months ago - 1 comment

#119 - 生成的语音开头有啪嗒的声音

Issue - State: open - Opened by zsanjin-p 8 months ago - 6 comments

#118 - 请问如何可以用代码形式来运行生成语音？

Issue - State: open - Opened by dsyrock 8 months ago - 1 comment

#117 - How much data samples would I need to fine tune a new voice with a stable prompt ?

Issue - State: open - Opened by JacopoMangiavacchi 8 months ago - 5 comments

#116 - Add a multi-thread one-step TTS inference script.

Pull Request - State: closed - Opened by duj12 8 months ago

#115 - Docker部署执行中文转TTS后异常崩溃 docker无法连接且假死

Issue - State: open - Opened by leceshide 8 months ago

#115 - Docker部署执行中文转TTS后异常崩溃 docker无法连接且假死

Issue - State: open - Opened by leceshide 8 months ago

#114 - training data CUDA error: out of memory

Issue - State: open - Opened by qihengzhw 8 months ago

#113 - 希望能提供Websocket API，方便我们提交TTS任务和接收结果

Issue - State: open - Opened by leceshide 8 months ago

#113 - 希望能提供Websocket API，方便我们提交TTS任务和接收结果

Issue - State: open - Opened by leceshide 8 months ago

#112 - Mac APP无法使用

Issue - State: open - Opened by Darlig 8 months ago - 1 comment
Labels: duplicate

#112 - Mac APP无法使用

Issue - State: open - Opened by Darlig 8 months ago - 1 comment
Labels: duplicate

#111 - 目前模型包含2000个声音，这个模型do_00140000大小1.2G，g_00140000大小200M，目前克隆声音10000步需要2个小时，可以提供一个小的训练模型吗，包含一个基础声音，用于克隆新的声音

Issue - State: open - Opened by zebraline 8 months ago

#111 - 目前模型包含2000个声音，这个模型do_00140000大小1.2G，g_00140000大小200M，目前克隆声音10000步需要2个小时，可以提供一个小的训练模型吗，包含一个基础声音，用于克隆新的声音

Issue - State: open - Opened by zebraline 8 months ago

#110 - 调低音量，结过有问题

Issue - State: open - Opened by youran1024 8 months ago

#110 - 调低音量，结过有问题

Issue - State: open - Opened by youran1024 8 months ago

#109 - 如何提高音量

Issue - State: open - Opened by youran1024 8 months ago - 3 comments

#108 - > 值得一提的是，我新克隆了一个音色，它对中文的效果很好，但是偶尔会掺杂一点点杂音。但是对英文的效果，读的流畅度不理想，更像是一个单词一个单词的念。我想请问，杂音的出现和英文流畅度问题分别是与数据前处理有关还是与预训练模型有关？

Issue - State: closed - Opened by li1213876867 8 months ago

#108 - > 值得一提的是，我新克隆了一个音色，它对中文的效果很好，但是偶尔会掺杂一点点杂音。但是对英文的效果，读的流畅度不理想，更像是一个单词一个单词的念。我想请问，杂音的出现和英文流畅度问题分别是与数据前处理有关还是与预训练模型有关？

Issue - State: closed - Opened by li1213876867 8 months ago

#107 - 请问如何调用本地部署起来的api?

Issue - State: open - Opened by lkyuier 8 months ago - 7 comments

#106 - 请问如何添加停顿

Issue - State: closed - Opened by youran1024 8 months ago - 2 comments

#105 - pip install -e .[train] 可能会修改torch的版本。

Issue - State: open - Opened by dkzyh87 9 months ago - 1 comment

#104 - 请问README.zh.md里的第一个小孩子的声音是哪个id？

Issue - State: open - Opened by dota2015 9 months ago

#103 - 英文大写拼读有问题，比如ABC、TTS等会读错

Issue - State: open - Opened by guogeer 9 months ago - 1 comment

#103 - 英文大写拼读有问题，比如ABC、TTS等会读错

Issue - State: open - Opened by guogeer 9 months ago - 1 comment

#102 - 训练模型，怎么把已有的英语数据转换为易魔声需要的格式

Issue - State: closed - Opened by songyinghao 9 months ago - 3 comments

#102 - 训练模型，怎么把已有的英语数据转换为易魔声需要的格式

Issue - State: closed - Opened by songyinghao 9 months ago - 3 comments

#101 - Step2：Run MFA ，need more description

Issue - State: open - Opened by li1213876867 9 months ago - 4 comments

#101 - Step2：Run MFA ，need more description

Issue - State: open - Opened by li1213876867 9 months ago - 4 comments

#100 - 使用DataBaker进行训练，原有模型2014个声音，speaker如何增加一个新声音，加了一个原有模型不匹配

Issue - State: open - Opened by zebraline 9 months ago - 1 comment

#100 - 使用DataBaker进行训练，原有模型2014个声音，speaker如何增加一个新声音，加了一个原有模型不匹配

Issue - State: open - Opened by zebraline 9 months ago - 1 comment

#99 - 查看文档中的voicelist，好像角色都是外国人。在哪能找到，中文角色的id列表？

Issue - State: open - Opened by eleven-monkey 9 months ago - 4 comments

#98 - pre-trained model in Spanish

Issue - State: open - Opened by komangulo 9 months ago - 3 comments

#97 - Instruction added on how to create a new language model

Pull Request - State: open - Opened by SyabAhmad 9 months ago - 1 comment

#97 - Instruction added on how to create a new language model

Pull Request - State: open - Opened by SyabAhmad 9 months ago - 1 comment

#96 - Январь

Issue - State: open - Opened by AndreyBobrov37 9 months ago - 1 comment

#95 - 推理时切换为自己训练的model，遇到了张量不统一的情况

Issue - State: closed - Opened by SongDI911 9 months ago - 2 comments

#94 - How to train a new language?

Issue - State: open - Opened by HobisPL 9 months ago - 5 comments

#93 - 您好，在demo推理阶段遇到了未知问题，想请教一下。

Issue - State: open - Opened by BookerShi 9 months ago - 1 comment

#92 - please check doc about pypinyin_dict

Issue - State: closed - Opened by a00147600 9 months ago - 1 comment

#92 - please check doc about pypinyin_dict

Issue - State: closed - Opened by a00147600 9 months ago - 1 comment

#91 - Support for intel Mac?

Issue - State: open - Opened by MelleNi 9 months ago - 3 comments

#91 - Support for intel Mac?

Issue - State: open - Opened by MelleNi 9 months ago - 3 comments

#90 - 调整语速

Pull Request - State: closed - Opened by john9405 9 months ago

#90 - 调整语速

Pull Request - State: closed - Opened by john9405 9 months ago

#89 - modify pypinyin-dict

Pull Request - State: closed - Opened by qingfengcss 9 months ago

#89 - modify pypinyin-dict

Pull Request - State: closed - Opened by qingfengcss 9 months ago

#88 - 英文合成时，句子开头会出现爆响及解决方案

Issue - State: open - Opened by lingyu123-su 9 months ago - 4 comments

#88 - 英文合成时，句子开头会出现爆响及解决方案

Issue - State: open - Opened by lingyu123-su 9 months ago - 4 comments

GitHub / netease-youdao/EmotiVoice issues and pull requests