Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / PlayVoice/whisper-vits-svc issues and pull requests
#196 - silerovad 在多进程中会卡主
Issue -
State: open - Opened by panxin801 5 months ago
#195 - 歌曲文件进行推理如何保留伴奏呀? 试了一下,貌似只有人声。
Issue -
State: open - Opened by accsky 5 months ago
#194 - Does anyone know if the whisper-ppg-largev2 or v3 model can train diffusion models and use them?
Issue -
State: closed - Opened by beikungg 5 months ago
- 1 comment
#193 - Increasing SVC inference speed
Issue -
State: open - Opened by KaikeWesleyReis 6 months ago
- 3 comments
#192 - 想修改模型架构为输出48k,不知道训练底模需要成本是多少?作者是用A100 80G训练的吗?7天 80 batch_size
Issue -
State: open - Opened by ILG2021 6 months ago
- 1 comment
#191 - sovits好像会抑制高频数据,导致输出的结果平平的,有没有参数可以调节,达到还原度最高?
Issue -
State: closed - Opened by ILG2021 6 months ago
#190 - 混合说话人参数时仅输出.spk.npy,没有输出模型,混合后的说话人参数怎么用?
Issue -
State: open - Opened by ShadowLoveElysia 6 months ago
#189 - 如何推理能产出48k的音频?
Issue -
State: closed - Opened by ILG2021 7 months ago
#188 - Missing data perturbation code in Data preprocessing.
Issue -
State: closed - Opened by MuruganR96 7 months ago
- 1 comment
#187 - Typo in README.md
Pull Request -
State: closed - Opened by Silvelter 7 months ago
#186 - 关于版权方面
Issue -
State: closed - Opened by ILG2021 8 months ago
- 2 comments
#185 - 怎么把whisper替换掉啊???可以把whisper替换为fast-whisper嘛,为什么替换掉whisper就可以实时语音转换了
Issue -
State: open - Opened by liushiguang 8 months ago
#184 - where the Timbre Encode come from?
Issue -
State: open - Opened by iamliulong 8 months ago
- 2 comments
#183 - 训练说话模型而非唱歌的问题
Issue -
State: closed - Opened by ILG2021 8 months ago
- 16 comments
#182 - 训练的时候GPU利用率较低
Issue -
State: closed - Opened by ILG2021 8 months ago
#181 - UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weig ht_norm.
Issue -
State: open - Opened by zdy121 8 months ago
- 3 comments
#180 - 奇怪的问题,GPU推理声音有部分失真,cpu推理正常
Issue -
State: closed - Opened by ILG2021 8 months ago
- 1 comment
#179 - 模型训练之后没有best.pt,能否改进?
Issue -
State: closed - Opened by ILG2021 9 months ago
#178 - 现在需要男歌手翻唱女声的歌曲,使用的是singer0008,因为软件没有变调功能,出来的效果不太行
Issue -
State: closed - Opened by ILG2021 9 months ago
- 2 comments
#177 - Pre-training model dataset questions in SO-VITS-SVC 5.0
Issue -
State: open - Opened by CHK-0000 9 months ago
- 1 comment
#176 - 5分多钟的歌,生成出来只有2分钟左右,这个是什么原因,我使用的是space中的代码
Issue -
State: closed - Opened by ILG2021 9 months ago
- 2 comments
#175 - 推理速度如何加快,CPU
Issue -
State: open - Opened by qqcykbz001 9 months ago
#174 - 推理是是否需要用分离后的人声部分进行推理
Issue -
State: open - Opened by leonfrank 9 months ago
- 1 comment
#173 - Error but show nothing(error).
Issue -
State: open - Opened by kikunayar 9 months ago
- 2 comments
#172 - About Numpy Version
Issue -
State: open - Opened by AiharaMahiru 9 months ago
#171 - 如何修改whisper的batch?
Issue -
State: open - Opened by sungh66 10 months ago
#170 - 除了音色转换,推理如何修改歌词呢?
Issue -
State: closed - Opened by juntaosun 10 months ago
- 2 comments
#169 - 请问CPU训练速度
Issue -
State: open - Opened by accsky 10 months ago
- 1 comment
#168 - ./data_svc/waves-16k 目录下没有任何东西
Issue -
State: open - Opened by accsky 10 months ago
- 1 comment
#167 - finetuning volumetry
Issue -
State: open - Opened by leonardoboulitreau 10 months ago
#166 - 可否能支持推理时指定多个wav文件
Issue -
State: closed - Opened by miyuren 10 months ago
#165 - 推理速度很慢,有什么解决的办法吗
Issue -
State: open - Opened by luyao-cv 10 months ago
- 1 comment
#164 - 训练的时候出的问题,该怎么解决?
Issue -
State: open - Opened by TMD1122 10 months ago
#163 - 这是为什么?因为版本的问题么,我的crepe是0.0.14。
Issue -
State: open - Opened by TMD1122 10 months ago
- 1 comment
#162 - Post-Inferred WAV files produced with blank spots
Issue -
State: closed - Opened by ThatJeffGuy 11 months ago
- 2 comments
#161 - fix wrong model wrong description
Pull Request -
State: closed - Opened by 00000000002 11 months ago
#160 - There's a bug here, and I tried to fix it. "/root/VITS/so-vits-svc-5.0-bigvgan-mix-v2/feature_retrieval/index.py"
Issue -
State: closed - Opened by Siegelth 11 months ago
- 2 comments
#159 - Is it better than RVC?
Issue -
State: open - Opened by loboere 11 months ago
- 2 comments
#158 - Reproduction of sovits5.0.pretrain.pth
Issue -
State: closed - Opened by leonardoboulitreau 11 months ago
- 2 comments
#157 - 音色还原,但是读音偶尔不标准,请问是什么原因
Issue -
State: closed - Opened by codexq123 11 months ago
- 3 comments
#156 - 推理时出了点问题
Issue -
State: closed - Opened by codexq123 11 months ago
- 1 comment
#155 - Retrieval model error
Issue -
State: open - Opened by dillfrescott 11 months ago
- 1 comment
#154 - Question about pitch(f0) hop_length
Issue -
State: closed - Opened by Gabibing 11 months ago
- 2 comments
#153 - Wondering how much promotion in noisy scene when adding perturbation
Issue -
State: open - Opened by Cheneng 11 months ago
- 1 comment
#152 - Fixed Colab miss-downloading problem
Pull Request -
State: closed - Opened by Fyphen1223 11 months ago
#151 - Added file downloading process for Colab that necessary for executing
Pull Request -
State: closed - Opened by Fyphen1223 11 months ago
- 1 comment
#150 - Unexpected issue: float division by zero
Issue -
State: closed - Opened by Fyphen1223 11 months ago
- 8 comments
#149 - 可以考虑在基本训练完之后加入强化学习,由人工对合成的音频进行测试排序并反馈
Issue -
State: closed - Opened by gjmhmm8 11 months ago
#148 - SLMGAN based discriminators
Issue -
State: open - Opened by thepowerfuldeez 12 months ago
- 1 comment
#147 - 模型有可能支持streaming使用吗?
Issue -
State: open - Opened by mega-cqz 12 months ago
- 2 comments
#146 - 预测出来的快歌 感觉软绵绵的,没有力度,响度还原了也不行
Issue -
State: open - Opened by NeilGY 12 months ago
- 1 comment
#145 - How do I remove pitch smoothening?
Issue -
State: open - Opened by Optic-the-Wolf 12 months ago
- 1 comment
#144 - Support for Whisper LargeV3
Pull Request -
State: closed - Opened by ShadowLoveElysia 12 months ago
#143 - 数据预处理遇到了问题
Issue -
State: open - Opened by chenguize 12 months ago
- 1 comment
#142 - ImportError: cannot import name 'consume_prefix_in_state_dict_if_present' from 'torch.nn.modules.utils' (/opt/miniconda3/envs/vc2/lib/python3.8/site-packages/torch/nn/modules/utils.py)
Issue -
State: open - Opened by EricPaul03 almost 1 year ago
- 6 comments
#141 - Openai他们up了WhisperV3的版本,考虑过在sovits测试一下V3用于特征提取的性能吗
Issue -
State: open - Opened by KIKscanf about 1 year ago
- 14 comments
#140 - diff_loss error while using GPU
Issue -
State: closed - Opened by bukhalmae145 about 1 year ago
#139 - 希望后续能有WebUI 浏览器可以操作的界面
Issue -
State: open - Opened by TomYule about 1 year ago
- 2 comments
#138 - Update README.md
Pull Request -
State: closed - Opened by vatsalya-vyas about 1 year ago
#137 - Something wrong with the Decoder.
Issue -
State: closed - Opened by bukhalmae145 about 1 year ago
- 10 comments
#136 - 合成说话语音的时候很奇怪
Issue -
State: open - Opened by kwaihua about 1 year ago
- 3 comments
#135 - Updating README.md
Pull Request -
State: closed - Opened by VivekGuruduttK28 about 1 year ago
#134 - fixed typo
Pull Request -
State: closed - Opened by vidyaa18 about 1 year ago
#133 - Will so-vits-svc 5.0 never be update from now?
Issue -
State: closed - Opened by NLPV2011 about 1 year ago
- 1 comment
#132 - 如何把两个model合并
Issue -
State: open - Opened by ryanjfdeng1 about 1 year ago
- 7 comments
#131 - pipeline
Issue -
State: closed - Opened by luyao-cv about 1 year ago
- 2 comments
#130 - svc_trainer.py error
Issue -
State: closed - Opened by bukhalmae145 about 1 year ago
- 45 comments
#129 - 报错
Issue -
State: open - Opened by ShadowLoveElysia about 1 year ago
- 4 comments
#128 - svc_export.py error
Issue -
State: closed - Opened by bukhalmae145 about 1 year ago
- 4 comments
#127 - whisper and hubert
Issue -
State: open - Opened by wblgers about 1 year ago
- 5 comments
Labels: good first issue
#126 - Keep getting this error message when starting training.
Issue -
State: open - Opened by PhilFW2 about 1 year ago
- 1 comment
#125 - 电音比较浓厚
Issue -
State: closed - Opened by luyao-cv about 1 year ago
- 12 comments
#124 - 不同性别歌手测试效果较差
Issue -
State: open - Opened by luyao-cv about 1 year ago
- 2 comments
#123 - 频谱图绘制
Issue -
State: closed - Opened by luyao-cv about 1 year ago
- 1 comment
#122 - 梯度累积(gradient accumulation)
Issue -
State: open - Opened by MaxMax2016 about 1 year ago
Labels: good first issue
#121 - 效果对比
Issue -
State: closed - Opened by luyao-cv about 1 year ago
- 13 comments
Labels: good first issue
#120 - whisper長度切割問題
Issue -
State: open - Opened by Taiwan1912 about 1 year ago
- 1 comment
#119 - When converting Chinese speech instead of singing voices, there are some issues with the tone
Issue -
State: closed - Opened by 450586509 about 1 year ago
- 3 comments
#118 - 使用svc_inference_post进行后置处理的时候发现损失很大
Issue -
State: closed - Opened by synuwxy about 1 year ago
- 2 comments
#117 - 感觉我这儿出了点问题
Issue -
State: closed - Opened by uuusername about 1 year ago
- 11 comments
#116 - 说话人音色做歌曲转换的问题
Issue -
State: closed - Opened by elissopp about 1 year ago
- 2 comments
#115 - Add conda env file, add missing dependencies
Pull Request -
State: closed - Opened by imedina7 about 1 year ago
#114 - demo中奇怪的模糊
Issue -
State: closed - Opened by YacratesWyh about 1 year ago
- 1 comment
#113 - which model did you make sovits5.0.pretrain.pth using?
Issue -
State: closed - Opened by AllInGood about 1 year ago
- 1 comment
#112 - about sovits5.0.pretrain.pth
Issue -
State: closed - Opened by aTeNaNt about 1 year ago
- 6 comments
#111 - x新的diff分支的训练的tensorboard中大量电音,这是正常情况吗
Issue -
State: open - Opened by KIKscanf about 1 year ago
- 12 comments
#110 - Inference having whitenoice
Issue -
State: closed - Opened by suda-ss about 1 year ago
#109 - inference result is too noisy
Issue -
State: closed - Opened by meriamOu about 1 year ago
- 1 comment
#108 - Model is not running on my local
Issue -
State: closed - Opened by suda-ss about 1 year ago
#107 - Contact
Issue -
State: closed - Opened by happy-machine about 1 year ago
#106 - Update svc_inference_batch.py
Pull Request -
State: closed - Opened by stillonearth about 1 year ago
#105 - Any reference docs for VAE perturbation?
Issue -
State: closed - Opened by wblgers about 1 year ago
- 2 comments
#104 - f0范围不合适导致的沙哑声
Issue -
State: open - Opened by zdj97 about 1 year ago
- 2 comments
#102 - 一种sepc变量来动态获取音频文件的采样率的预处理以适应更高采样率
Issue -
State: closed - Opened by KIKscanf about 1 year ago
- 1 comment
#101 - Introduce RVC TopK retrieval feature
Issue -
State: closed - Opened by MuruganR96 about 1 year ago
- 1 comment
#100 - Suggestions needed to improve speaker similarity
Issue -
State: closed - Opened by MuruganR96 about 1 year ago
- 4 comments
#99 - 一种推理任务的cpu并行处理
Issue -
State: open - Opened by KIKscanf about 1 year ago
#98 - svc 4 vs 5
Issue -
State: closed - Opened by gitihobo over 1 year ago
- 1 comment
#97 - NCCL error with multi gpu on windows
Issue -
State: closed - Opened by crankyz over 1 year ago
- 2 comments
#96 - Colab 可以更新一下吗?谢谢
Issue -
State: closed - Opened by fodlkfjasuqwenc12134672 over 1 year ago