Retrieval-based-Voice-Conversion-WebUI icon indicating copy to clipboard operation
Retrieval-based-Voice-Conversion-WebUI copied to clipboard

Easily train a good VC model with voice data <= 10 mins!

Results 863 Retrieval-based-Voice-Conversion-WebUI issues
Sort by recently updated
recently updated
newest added

I am attempting to add more voices to my local Piper TTS. I found [this repo](https://huggingface.co/QuickWick/Music-AI-Voices/tree/main) that contains several pre-trained models. It seems that I can convert from the downloaded...

环境: RVC版本:[https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI.git](url) -- RVC的git仓库最新提交版本 使用以下脚本导出的onnx:[https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/main/tools/export_onnx.py](url) 原模型为rvc自带的keruanV1.pth,导出模型为keruanV1.onnx,确认生成的是动态模型。 现象: 由于是做实时变声推理,因此每次送入模型的数据片段会很短,大概7200个采样。但输出的数据片段并不能很好的衔接在一起。如:片段A、B、C,在从麦克风进来后,三个数据片段的声音是连续的,但从变声器出来后,听感上A会高一些,B会低一些,而且三个片段的衔接处也无法丝滑过渡,会导致衔接处播放时产生噪音。实际听感就是,变声后的声音会周期性出现“点点点”的声音。 所做的尝试: 1. 参考[https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/main/gui_v1.py](url)中对推理后数据的处理。增加了交叉淡化算法,但收效甚微。 ``` // 计算当前返回帧的头部淡化效果 auto fo_head = in_buf + sola_offset; auto fo_tail = fo_head + block_frame; for (size_t i =...

Lol # Pull request checklist - [x] The PR has a proper title. Use [Semantic Commit Messages](https://seesparkbox.com/foundry/semantic_commit_messages). (No more branch-name title please) - [x] Make sure this is ready to...

我在使用onnx_inference_demo.py测试onnx的实时变声推理效果。 由于需要满足延迟小的要求,因此测试时会将读入的音频文件按照一片6400 pcm的大小切分。 然后循环送入demo中,但发现推理后,每片输出数据的开始和结尾处会存在杂音。 ![image](https://github.com/user-attachments/assets/e83a0f74-48f3-49a5-81b2-ba495e201631) 怀疑是hubert在对片段的前后部分编码时由于没有参考帧,所以编成了杂音。 我使用的编码器模型为vec-768-layer-12.onnx 使用的音色模型是用RVC自带的export_onnx.py导出的动态Onnx模型(参考isses1830解决) 请问是否有方法解决这个杂音问题?

Traceback (most recent call last): File "C:\RVC-beta\RVC-beta0717\runtime\lib\site-packages\gradio\routes.py", line 321, in run_predict output = await app.blocks.process_api( File "C:\RVC-beta\RVC-beta0717\runtime\lib\site-packages\gradio\blocks.py", line 1007, in process_api data = self.postprocess_data(fn_index, result["prediction"], state) File "C:\RVC-beta\RVC-beta0717\runtime\lib\site-packages\gradio\blocks.py", line 953,...

while running inference coming across this error . 2024-09-11 11:17:28 | INFO | infer.modules.vc.modules | Get sid: guanguanV1.pth 2024-09-11 11:17:28 | INFO | infer.modules.vc.modules | Loading: assets/weights/guanguanV1.pth 2024-09-11 11:17:28 |...

i am getting this error when trying to train the model on any files

哪位大佬有在VCTK数据集上的48k的预训练模型对应的added.index索引文件?

![Uploading 311478923-3b77dc86-3c73-4232-8211-2838bbe9c279.p ng…]()

![Uploading 311478923-3b77dc86-3c73-4232-8211-2838bbe9c279.png…]()