Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / RVC-Boss/GPT-SoVITS issues and pull requests
#1935 - 导出的文本读音错误,麻烦大佬看一下
Issue -
State: closed - Opened by AkebiKomichi about 1 month ago
- 7 comments
#1934 - 是否支持长音频克隆
Issue -
State: open - Opened by xipingL about 1 month ago
- 1 comment
#1933 - 为什么英文TikTok,念出来会是T I K T O K? 是一个字母一个字母念的啊?
Issue -
State: open - Opened by skyhhuc about 1 month ago
- 14 comments
#1932 - Inconsistent Pronunciation of "BAN/ban" and "BUFF/buff" in GPT-SoVITS
Issue -
State: open - Opened by Strive-for-excellence about 1 month ago
#1931 - +[Trending√ZVIDEOs!] 𝙾𝚗𝚎 𝙶𝚒𝚛𝚕 𝚘𝚗𝚎 𝙵𝚛𝚘𝚐 𝚅𝚒𝚛𝚊𝚕 𝚕𝚎𝚊𝚔𝚎𝚍 Video 2024 LINK On Social Media X Twitter [MMS72K]
Issue -
State: closed - Opened by Wigfallxz about 1 month ago
- 1 comment
#1930 - _pickle.UnpicklingError: pickle data was truncated 和 process 0 terminated with exit code 3221225477
Issue -
State: open - Opened by dfdr557 about 1 month ago
#1929 - 预训练模型问题
Issue -
State: closed - Opened by shawnxox5173682 about 1 month ago
- 2 comments
#1928 - 数字转汉字念法问题
Issue -
State: open - Opened by wewaa about 1 month ago
#1927 - 高版本的pytorch(2.7.0)会出现错误,请社区酌情处理
Issue -
State: closed - Opened by willwilling about 1 month ago
- 6 comments
#1926 - 在colab运行gpt微调时遇到错误 RuntimeError: Index tensor must have the same number of dimensions as self tensor
Issue -
State: closed - Opened by AmemiaErika about 1 month ago
- 4 comments
Labels: In follow-up
#1925 - api_v2接口碰到英文就会报错,有大佬会吗 求助!
Issue -
State: closed - Opened by kkkwjr about 1 month ago
- 2 comments
#1924 - webui内服务调用问题以及不使用webui如何开启GPT微调的多卡训练
Issue -
State: closed - Opened by MCXCC303 about 2 months ago
- 6 comments
#1923 - 如何用保存的weight/checkpoint进行二次训练? (没存log)
Issue -
State: closed - Opened by Bobchenyx about 2 months ago
- 1 comment
#1922 - 제발 왜 한국어tts가 작동하지 않는 것일까요?
Issue -
State: open - Opened by ahzy-ciel about 2 months ago
- 2 comments
#1921 - 关于freeze_quantizer的写法
Issue -
State: open - Opened by wzy3650 about 2 months ago
- 1 comment
Labels: In follow-up
#1920 - Quality: systhesized audio voice doesnt match the voice of input reference audio
Issue -
State: open - Opened by siddharthbhurat4 about 2 months ago
#1919 - 请问这个模型能做低延迟的文本转语音功能么?类似实时流式输出转语音
Issue -
State: open - Opened by Rosejacka about 2 months ago
- 5 comments
#1918 - fix wrong path
Pull Request -
State: closed - Opened by v3ucn about 2 months ago
#1917 - Fix bug processing duplicate punctuation in TextPreprocessor.py
Pull Request -
State: open - Opened by horenbergerb about 2 months ago
#1916 - 生成的音频在16000hz有明显断层,如何设置可以
Issue -
State: closed - Opened by tuoerye about 2 months ago
- 1 comment
#1915 - 1B微调训练和ASR中的报错麻烦处理一下
Issue -
State: closed - Opened by AkebiKomichi about 2 months ago
- 1 comment
#1914 - Fedora41 语音降噪工具报错
Issue -
State: open - Opened by AXFOX about 2 months ago
#1913 - could it support cpu inference?
Issue -
State: closed - Opened by sutungpo about 2 months ago
- 3 comments
#1912 - 一键三连之后,微调模型的时候提示CUFFT errOr: CUFFT NOT IMPLEMENTED
Issue -
State: open - Opened by Holferzhang about 2 months ago
#1912 - 一键三连之后,微调模型的时候提示CUFFT errOr: CUFFT NOT IMPLEMENTED
Issue -
State: open - Opened by Holferzhang about 2 months ago
#1911 - 大家有炼出特别满意的模型吗?有没有比我的这个更好的,不妨分享一下,拿来听书用。
Issue -
State: open - Opened by jiekemt about 2 months ago
- 5 comments
#1910 - linux下通过gradio_client调用uvr5的uvr_convert()接口报httpcore.ConnectError错误
Issue -
State: open - Opened by hezilon about 2 months ago
#1910 - linux下通过gradio_client调用uvr5的uvr_convert()接口报httpcore.ConnectError错误
Issue -
State: open - Opened by hezilon about 2 months ago
#1909 - ImportError: cannot import name 'ComponentDefinitionError' from 'gradio.exceptions'
Issue -
State: open - Opened by AkebiKomichi about 2 months ago
- 1 comment
#1908 - 更新 TTS-AGI/TTS-Arena上的GPT-Sovits v2模型
Issue -
State: open - Opened by Pevernow about 2 months ago
- 5 comments
Labels: In follow-up
#1906 - 请问如何在文字中插入停顿呢?
Issue -
State: open - Opened by tuoerye about 2 months ago
- 3 comments
#1905 - 9950x-指定ccd0 4080 速度大概300it/s
Issue -
State: open - Opened by kawae0709 about 2 months ago
- 9 comments
#1893 - GPT训练报错,未生成模型文件
Issue -
State: closed - Opened by xiaoowen about 2 months ago
- 5 comments
#1892 - Do you have any plans for a new release?
Issue -
State: open - Opened by GalenMarek14 about 2 months ago
- 8 comments
Labels: todolist
#1892 - Do you have any plans for a new release?
Issue -
State: open - Opened by GalenMarek14 about 2 months ago
- 2 comments
Labels: todolist
#1891 - _pickle.UnpicklingError: invalid load key, 'v'.
Issue -
State: closed - Opened by xiujiePei about 2 months ago
- 2 comments
#1891 - _pickle.UnpicklingError: invalid load key, 'v'.
Issue -
State: closed - Opened by xiujiePei about 2 months ago
- 2 comments
#1886 - 大佬们,在文本获取这一步失败了,该如何解决啊
Issue -
State: closed - Opened by Anh0923 about 2 months ago
- 3 comments
#1885 - 中文asr乱码
Issue -
State: closed - Opened by Surrin1999 2 months ago
- 2 comments
#1882 - logs下面的文件能删吗?
Issue -
State: closed - Opened by Lixi20 2 months ago
- 4 comments
#1881 - 请问推理时,如何增加句子间的停顿时间呢?
Issue -
State: closed - Opened by WinSure 2 months ago
- 3 comments
#1875 - 成功跑通一次后,第二次在SSL阶段爆显存了
Issue -
State: open - Opened by Roy2029 2 months ago
#1874 - 中文启动代码
Issue -
State: closed - Opened by hk1996yhx 2 months ago
#1873 - 流式推理启动速度
Issue -
State: closed - Opened by ZxnSnowy 2 months ago
- 1 comment
#1872 - Fix g2pw bug
Pull Request -
State: closed - Opened by wjddd 2 months ago
#1853 - Is there a research paper for this repository?
Issue -
State: closed - Opened by Typhoon0303 2 months ago
- 1 comment
#1852 - 加载Keira_e8_s96.pth错误
Issue -
State: closed - Opened by ZxnSnowy 2 months ago
#1851 - Whisper didn’t use System Agent to download | Whisper模型下载不走系统代理
Issue -
State: closed - Opened by Luke2049 2 months ago
- 6 comments
#1850 - 文字一长就不行了吗?RuntimeError: The size of tensor a (857) must match the size of tensor b (512) at non-singleton dimension 1
Issue -
State: closed - Opened by gg22mm 2 months ago
- 3 comments
#1849 - 使用命令行完成数据集的音频切分的方式:audio_slicer.py 这个文件找不到?
Issue -
State: open - Opened by wewaa 2 months ago
- 1 comment
Labels: todolist
#1848 - 添加自己修改的一些webui功能
Pull Request -
State: closed - Opened by katana8188 2 months ago
#1847 - 在执行推理时出现如下错误
Issue -
State: open - Opened by flyice8 2 months ago
- 1 comment
#1846 - 大佬们我想训练英文的语音训练模型需要换吗?
Issue -
State: closed - Opened by flyice8 2 months ago
- 4 comments
#1845 - 有从cnhubert出来的音频特征和文本特征进行对齐的模型吗?
Issue -
State: open - Opened by MonolithFoundation 2 months ago
#1844 - api_v2 服务启动后,连续调用时,有时候第一句会变为上一次调用的最后一句
Issue -
State: open - Opened by Vocanic-eruption 2 months ago
- 4 comments
#1843 - 0%| | 0/3 [00:00<?, ?it/s] 程序卡住
Issue -
State: closed - Opened by selfnat 2 months ago
#1842 - 每训练一个模型磁盘空间便被占用3G空间,还找不到文件?
Issue -
State: open - Opened by 99101617 2 months ago
- 5 comments
#1841 - onnx_dereverb_By_FoxJoy无法使用GPU加速有解决办法吗?
Issue -
State: open - Opened by 99101617 2 months ago
- 1 comment
#1840 - api_v2.py 如何关闭推理进度条
Issue -
State: closed - Opened by selfnat 2 months ago
- 2 comments
#1839 - 推理时卡住了,请问是什么原因?
Issue -
State: closed - Opened by WeimianLI 2 months ago
- 3 comments
#1838 - 优化infer_webui代码,支持上传多个主参考音频快捷切换
Pull Request -
State: open - Opened by Cosmo-klara 2 months ago
#1837 - tts接口使用流式推理,经常出现卡死,此时cpu利用率为99%-101%之间
Issue -
State: closed - Opened by lishq 2 months ago
#1836 - IndexError: tuple index out of range
Issue -
State: open - Opened by surjayc 2 months ago
#1835 - Macos15无法安装ffmpeg
Issue -
State: open - Opened by irise-tech 2 months ago
#1834 - ui language does not change no matter what i try
Issue -
State: open - Opened by linuarM 2 months ago
- 11 comments
#1833 - v2到最后一步为什么不能变声啊
Issue -
State: closed - Opened by 2464634492 2 months ago
- 4 comments
#1832 - V2生成的音频末尾偶现波形被截断的问题
Issue -
State: closed - Opened by EnneaCode 3 months ago
- 2 comments
#1831 - 小概率任务失败,日志提示子进程挂了 Child process die
Issue -
State: closed - Opened by aj-web 3 months ago
#1830 - Need HELP! Infer Audio is Blank when I Train the model in Arabic and try to infer it.
Issue -
State: open - Opened by Anas-KhanWP 3 months ago
- 3 comments
#1829 - No module named 'tools.my_utils'
Issue -
State: closed - Opened by GlowingBrick 3 months ago
- 2 comments
#1828 - How to Reduce Wind-like Noises and Lengthy Responses in Sigh-like Sound Generation?
Issue -
State: closed - Opened by k-min9 3 months ago
- 1 comment
#1827 - 训练的数据集有什么要点
Issue -
State: closed - Opened by QWXL 3 months ago
- 2 comments
#1826 - v2朗读质量提升很多,但是遇到几个问题
Issue -
State: open - Opened by gaord 3 months ago
- 1 comment
#1826 - v2朗读质量提升很多,但是遇到几个问题
Issue -
State: open - Opened by gaord 3 months ago
- 2 comments
#1825 - workers设置2以上后多进程串音频
Issue -
State: open - Opened by hxb112266 3 months ago
- 1 comment
Labels: bug, todolist
#1824 - 关于打标环节的PermissionError: [Errno 13] Permission denied:
Issue -
State: closed - Opened by qiaokelihahaj 3 months ago
- 1 comment
#1823 - Added three new API v2 endpoints to list audio files, gpt files and sovit files.
Pull Request -
State: open - Opened by cpumaxx 3 months ago
#1822 - yamlに日本語があった場合文字化けで読み取れずエラーになるため読み取り時にエンコーディングを追加
Pull Request -
State: closed - Opened by ootsuka-repos 3 months ago
#1821 - api_v2无法生成中文外的语音
Issue -
State: closed - Opened by tuhang 3 months ago
- 3 comments
#1820 - 训练sovits底模,数据量问题
Issue -
State: closed - Opened by yc930401 3 months ago
- 1 comment
#1819 - uvr5使用onnx_dereverb模型未使用gpu推理,建议在requirements.txt里指定onnxruntime-gpu为1.18.1版本
Issue -
State: open - Opened by huanlingfy 3 months ago
- 1 comment
#1818 - wsl2 amd rocm6.1.3 训练时出现以下错误
Issue -
State: closed - Opened by AMD7900XTX 3 months ago
- 4 comments
#1817 - 使用自训练模型API 报错:/api/modules HTTP/1. 1" 404 Not Found
Issue -
State: open - Opened by Thelast0802 3 months ago
- 5 comments
#1816 - How much improvement in training quality can I expect from using a 3-hour audio dataset compared to a 30-minute one?
Issue -
State: open - Opened by Nisekoi-1 3 months ago
- 1 comment
#1815 - feat: update import path
Pull Request -
State: open - Opened by gxdai 3 months ago
#1814 - feat: update gpt_sovits
Pull Request -
State: closed - Opened by gxdai 3 months ago
#1813 - 如何精确控制输出音频的长度?
Issue -
State: closed - Opened by MonolithFoundation 3 months ago
- 3 comments
#1812 - Testing issues with streaming interfaces,
Issue -
State: open - Opened by zhuangzhuangliu2345 3 months ago
#1811 - 为api_v2增加接受base64编码的reference audio文件的功能
Pull Request -
State: open - Opened by 0000sir 3 months ago
- 2 comments
#1810 - 运行api_v2时报错了,没看懂是什么问题
Issue -
State: closed - Opened by pgz100 3 months ago
- 2 comments
#1809 - 运行api_v2.py时报错CUDA不可用
Issue -
State: closed - Opened by pgz100 3 months ago
- 2 comments
#1808 - Added some missing command-line options to inference_cli.py
Pull Request -
State: open - Opened by hydrusbeta 3 months ago
#1807 - Support for Korean language fine-tuning
Issue -
State: closed - Opened by Typhoon0303 3 months ago
- 2 comments
#1806 - 长文本生成时,提取文本Bert特征时花费的时间很长
Issue -
State: open - Opened by hjj-lmx 3 months ago
#1805 - 控制台会打印出text_normalize 后长度不一致,是什么原因
Issue -
State: closed - Opened by hjj-lmx 3 months ago
#1804 - fix memory overflow issue in get-hubert-wav
Pull Request -
State: closed - Opened by kemingc-cmu-F24 3 months ago
- 1 comment
#1803 - SSL特征提取,爆内存问题
Issue -
State: open - Opened by kemingc-cmu-F24 3 months ago
- 1 comment
Labels: In follow-up
#1802 - 流式接口,所有语音合成完毕后才输出语音
Issue -
State: open - Opened by zhuangzhuangliu2345 3 months ago
- 2 comments
#1801 - chinese_bert引用不到
Issue -
State: open - Opened by hjj-lmx 3 months ago
#1800 - 粤语的参考音,对应的参考文字应该是什么样的
Issue -
State: open - Opened by hjj-lmx 3 months ago
- 1 comment