Merge pull request #234 from svc-develop-team/4.1-Stable
To Latest for synchronous
This commit is contained in:
commit
4bbb786244
27
README.md
27
README.md
|
@ -2,7 +2,7 @@
|
|||
|
||||
[**English**](./README.md) | [**中文简体**](./README_zh_CN.md)
|
||||
|
||||
#### ✨ A studio that contains f0 curve editor, speaker mix timeline editor and other features (The purpose of the Onnx model) : [MoeVoiceStudio(Comming soon)](https://github.com/NaruseMioShirakana/MoeVoiceStudio)
|
||||
#### ✨ A studio that contains f0 curve editor, speaker mix timeline editor and other features (The purpose of the Onnx model) : [MoeVoiceStudio](https://github.com/NaruseMioShirakana/MoeVoiceStudio)
|
||||
|
||||
#### ✨ A fork with a greatly improved interface: [34j/so-vits-svc-fork](https://github.com/34j/so-vits-svc-fork)
|
||||
|
||||
|
@ -446,6 +446,29 @@ Use [onnx_export.py](https://github.com/svc-develop-team/so-vits-svc/blob/4.0/on
|
|||
|
||||
Note: For Hubert Onnx models, please use the models provided by MoeSS. Currently, they cannot be exported on their own (Hubert in fairseq has many unsupported operators and things involving constants that can cause errors or result in problems with the input/output shape and results when exported.)
|
||||
|
||||
|
||||
## 📎 Reference
|
||||
|
||||
| URL | Designation | Title | Implementation Source |
|
||||
| --- | ----------- | ----- | --------------------- |
|
||||
|[2106.06103](https://arxiv.org/abs/2106.06103) | VITS (Synthesizer)| Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech | [jaywalnut310/vits](https://github.com/jaywalnut310/vits) |
|
||||
|[2111.02392](https://arxiv.org/abs/2111.02392) | SoftVC (Speech Encoder)| A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion | [bshall/hubert](https://github.com/bshall/hubert) |
|
||||
|[2204.09224](https://arxiv.org/abs/2204.09224) | ContentVec (Speech Encoder)| ContentVec: An Improved Self-Supervised Speech Representation by Disentangling Speakers | [auspicious3000/contentvec](https://github.com/auspicious3000/contentvec) |
|
||||
|[2212.04356](https://arxiv.org/abs/2212.04356) | Whisper (Speech Encoder) | Robust Speech Recognition via Large-Scale Weak Supervision | [openai/whisper](https://github.com/openai/whisper) |
|
||||
|[2110.13900](https://arxiv.org/abs/2110.13900) | WavLM (Speech Encoder) | WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing | [microsoft/unilm/wavlm](https://github.com/microsoft/unilm/tree/master/wavlm) |
|
||||
|[2305.17651](https://arxiv.org/abs/2305.17651) | DPHubert (Speech Encoder) | DPHuBERT: Joint Distillation and Pruning of Self-Supervised Speech Models | [pyf98/DPHuBERT](https://github.com/pyf98/DPHuBERT) |
|
||||
|[DOI:10.21437/Interspeech.2017-68](http://dx.doi.org/10.21437/Interspeech.2017-68) | Harvest (F0 Predictor) | Harvest: A high-performance fundamental frequency estimator from speech signals | [mmorise/World/harvest](https://github.com/mmorise/World/blob/master/src/harvest.cpp) |
|
||||
|[aes35-000039](https://www.aes.org/e-lib/online/browse.cfm?elib=15165) | Dio (F0 Predictor) | Fast and reliable F0 estimation method based on the period extraction of vocal fold vibration of singing voice and speech | [mmorise/World/dio](https://github.com/mmorise/World/blob/master/src/dio.cpp) |
|
||||
|[8461329](https://ieeexplore.ieee.org/document/8461329) | Crepe (F0 Predictor) | Crepe: A Convolutional Representation for Pitch Estimation | [maxrmorrison/torchcrepe](https://github.com/maxrmorrison/torchcrepe) |
|
||||
|[DOI:10.1016/j.wocn.2018.07.001](https://doi.org/10.1016/j.wocn.2018.07.001) | Parselmouth (F0 Predictor) | Introducing Parselmouth: A Python interface to Praat | [YannickJadoul/Parselmouth](https://github.com/YannickJadoul/Parselmouth) |
|
||||
|[2010.05646](https://arxiv.org/abs/2010.05646) | HIFIGAN (Vocoder) | HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis | [jik876/hifi-gan](https://github.com/jik876/hifi-gan) |
|
||||
|[1810.11946](https://arxiv.org/abs/1810.11946.pdf) | NSF (Vocoder) | Neural source-filter-based waveform model for statistical parametric speech synthesis | [openvpi/DiffSinger/modules/nsf_hifigan](https://github.com/openvpi/DiffSinger/tree/refactor/modules/nsf_hifigan)
|
||||
|[2006.08195](https://arxiv.org/abs/2006.08195) | Snake (Vocoder) | Neural Networks Fail to Learn Periodic Functions and How to Fix It | [EdwardDixon/snake](https://github.com/EdwardDixon/snake)
|
||||
|[2105.02446v3](https://arxiv.org/abs/2105.02446v3) | Shallow Diffusion (PostProcessing)| DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism | [CNChTu/Diffusion-SVC](https://github.com/CNChTu/Diffusion-SVC) |
|
||||
|[K-means](https://citeseerx.ist.psu.edu/viewdoc/download;jsessionid=01D65490BADCC216F350D06F84D721AD?doi=10.1.1.308.8619&rep=rep1&type=pdf) | Feature K-means Clustering (PreProcessing)| Some methods for classification and analysis of multivariate observations | This repo |
|
||||
| | Feature TopK Retrieval (PreProcessing)| Retrieval based Voice Conversion | [RVC-Project/Retrieval-based-Voice-Conversion-WebUI](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI) |
|
||||
|
||||
|
||||
## ☀️ Previous contributors
|
||||
|
||||
For some reason the author deleted the original repository. Because of the negligence of the organization members, the contributor list was cleared because all files were directly reuploaded to this repository at the beginning of the reconstruction of this repository. Now add a previous contributor list to README.md.
|
||||
|
@ -488,6 +511,8 @@ For some reason the author deleted the original repository. Because of the negli
|
|||
|
||||
#### 《[中华人民共和国民法典](http://gongbao.court.gov.cn/Details/51eb6750b8361f79be8f90d09bc202.html)》
|
||||
|
||||
#### 《[中华人民共和国合同法](http://www.npc.gov.cn/zgrdw/npc/lfzt/rlyw/2016-07/01/content_1992739.htm)》
|
||||
|
||||
## 💪 Thanks to all contributors for their efforts
|
||||
<a href="https://github.com/svc-develop-team/so-vits-svc/graphs/contributors" target="_blank">
|
||||
<img src="https://contrib.rocks/image?repo=svc-develop-team/so-vits-svc" />
|
||||
|
|
|
@ -1,10 +1,8 @@
|
|||
# 马上要高考了,SvcDevelopTeam在此助各位考生高考旗开得胜,超常发挥。
|
||||
|
||||
# SoftVC VITS Singing Voice Conversion
|
||||
|
||||
[**English**](./README.md) | [**中文简体**](./README_zh_CN.md)
|
||||
|
||||
#### ✨ 带有F0曲线编辑器,角色混合时间轴编辑器的推理端 (Onnx模型的用途) : [MoeVoiceStudio(即将到来)](https://github.com/NaruseMioShirakana/MoeVoiceStudio)
|
||||
#### ✨ 带有F0曲线编辑器,角色混合时间轴编辑器的推理端 (Onnx模型的用途) : [MoeVoiceStudio](https://github.com/NaruseMioShirakana/MoeVoiceStudio)
|
||||
|
||||
#### ✨ 改善了交互的一个分支推荐:[34j/so-vits-svc-fork](https://github.com/34j/so-vits-svc-fork)
|
||||
|
||||
|
@ -448,6 +446,28 @@ python compress_model.py -c="configs/config.json" -i="logs/44k/G_30400.pth" -o="
|
|||
|
||||
注意:Hubert Onnx模型请使用MoeSS提供的模型,目前无法自行导出(fairseq中Hubert有不少onnx不支持的算子和涉及到常量的东西,在导出时会报错或者导出的模型输入输出shape和结果都有问题)
|
||||
|
||||
|
||||
## 📎 引用及论文
|
||||
|
||||
| URL | 名称 | 标题 | 源码 |
|
||||
| --- | ----------- | ----- | --------------------- |
|
||||
|[2106.06103](https://arxiv.org/abs/2106.06103) | VITS (Synthesizer)| Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech | [jaywalnut310/vits](https://github.com/jaywalnut310/vits) |
|
||||
|[2111.02392](https://arxiv.org/abs/2111.02392) | SoftVC (Speech Encoder)| A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion | [bshall/hubert](https://github.com/bshall/hubert) |
|
||||
|[2204.09224](https://arxiv.org/abs/2204.09224) | ContentVec (Speech Encoder)| ContentVec: An Improved Self-Supervised Speech Representation by Disentangling Speakers | [auspicious3000/contentvec](https://github.com/auspicious3000/contentvec) |
|
||||
|[2212.04356](https://arxiv.org/abs/2212.04356) | Whisper (Speech Encoder) | Robust Speech Recognition via Large-Scale Weak Supervision | [openai/whisper](https://github.com/openai/whisper) |
|
||||
|[2110.13900](https://arxiv.org/abs/2110.13900) | WavLM (Speech Encoder) | WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing | [microsoft/unilm/wavlm](https://github.com/microsoft/unilm/tree/master/wavlm) |
|
||||
|[2305.17651](https://arxiv.org/abs/2305.17651) | DPHubert (Speech Encoder) | DPHuBERT: Joint Distillation and Pruning of Self-Supervised Speech Models | [pyf98/DPHuBERT](https://github.com/pyf98/DPHuBERT) |
|
||||
|[DOI:10.21437/Interspeech.2017-68](http://dx.doi.org/10.21437/Interspeech.2017-68) | Harvest (F0 Predictor) | Harvest: A high-performance fundamental frequency estimator from speech signals | [mmorise/World/harvest](https://github.com/mmorise/World/blob/master/src/harvest.cpp) |
|
||||
|[aes35-000039](https://www.aes.org/e-lib/online/browse.cfm?elib=15165) | Dio (F0 Predictor) | Fast and reliable F0 estimation method based on the period extraction of vocal fold vibration of singing voice and speech | [mmorise/World/dio](https://github.com/mmorise/World/blob/master/src/dio.cpp) |
|
||||
|[8461329](https://ieeexplore.ieee.org/document/8461329) | Crepe (F0 Predictor) | Crepe: A Convolutional Representation for Pitch Estimation | [maxrmorrison/torchcrepe](https://github.com/maxrmorrison/torchcrepe) |
|
||||
|[DOI:10.1016/j.wocn.2018.07.001](https://doi.org/10.1016/j.wocn.2018.07.001) | Parselmouth (F0 Predictor) | Introducing Parselmouth: A Python interface to Praat | [YannickJadoul/Parselmouth](https://github.com/YannickJadoul/Parselmouth) |
|
||||
|[2010.05646](https://arxiv.org/abs/2010.05646) | HIFIGAN (Vocoder) | HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis | [jik876/hifi-gan](https://github.com/jik876/hifi-gan) |
|
||||
|[1810.11946](https://arxiv.org/abs/1810.11946.pdf) | NSF (Vocoder) | Neural source-filter-based waveform model for statistical parametric speech synthesis | [openvpi/DiffSinger/modules/nsf_hifigan](https://github.com/openvpi/DiffSinger/tree/refactor/modules/nsf_hifigan)
|
||||
|[2006.08195](https://arxiv.org/abs/2006.08195) | Snake (Vocoder) | Neural Networks Fail to Learn Periodic Functions and How to Fix It | [EdwardDixon/snake](https://github.com/EdwardDixon/snake)
|
||||
|[2105.02446v3](https://arxiv.org/abs/2105.02446v3) | Shallow Diffusion (PostProcessing)| DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism | [CNChTu/Diffusion-SVC](https://github.com/CNChTu/Diffusion-SVC) |
|
||||
|[K-means](https://citeseerx.ist.psu.edu/viewdoc/download;jsessionid=01D65490BADCC216F350D06F84D721AD?doi=10.1.1.308.8619&rep=rep1&type=pdf) | Feature K-means Clustering (PreProcessing)| Some methods for classification and analysis of multivariate observations | 本代码库 |
|
||||
| | Feature TopK Retrieval (PreProcessing)| Retrieval based Voice Conversion | [RVC-Project/Retrieval-based-Voice-Conversion-WebUI](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI) |
|
||||
|
||||
## ☀️ 旧贡献者
|
||||
|
||||
因为某些原因原作者进行了删库处理,本仓库重建之初由于组织成员疏忽直接重新上传了所有文件导致以前的contributors全部木大,现在在README里重新添加一个旧贡献者列表
|
||||
|
@ -490,6 +510,8 @@ python compress_model.py -c="configs/config.json" -i="logs/44k/G_30400.pth" -o="
|
|||
|
||||
#### 《[中华人民共和国民法典](http://gongbao.court.gov.cn/Details/51eb6750b8361f79be8f90d09bc202.html)》
|
||||
|
||||
#### 《[中华人民共和国合同法](http://www.npc.gov.cn/zgrdw/npc/lfzt/rlyw/2016-07/01/content_1992739.htm)》
|
||||
|
||||
## 💪 感谢所有的贡献者
|
||||
<a href="https://github.com/svc-develop-team/so-vits-svc/graphs/contributors" target="_blank">
|
||||
<img src="https://contrib.rocks/image?repo=svc-develop-team/so-vits-svc" />
|
||||
|
|
|
@ -163,8 +163,8 @@
|
|||
"#@markdown Although the pretrained model generally does not cause any copyright problems, please pay attention to it. For example, ask the author in advance, or the author has indicated the feasible use in the description clearly.\n",
|
||||
"\n",
|
||||
"download_pretrained_model = True #@param {type:\"boolean\"}\n",
|
||||
"D_0_URL = \"https://huggingface.co/datasets/ms903/sovits4.0-768vec-layer12/resolve/main/sovits_768l12_pre_large_320k/clean_D_320000.pth\" #@param {type:\"string\"}\n",
|
||||
"G_0_URL = \"https://huggingface.co/datasets/ms903/sovits4.0-768vec-layer12/resolve/main/sovits_768l12_pre_large_320k/clean_G_320000.pth\" #@param {type:\"string\"}\n",
|
||||
"D_0_URL = \"https://huggingface.co/datasets/ms903/sovits4.0-768vec-layer12/resolve/main/sovits_768l12_pre_large_320k/clean_D_320000.pth\" #@param [\"https://huggingface.co/datasets/ms903/sovits4.0-768vec-layer12/resolve/main/sovits_768l12_pre_large_320k/clean_D_320000.pth\", \"https://huggingface.co/1asbgdh/sovits4.0-volemb-vec768/resolve/main/clean_D_320000.pth\"] {allow-input: true}\n",
|
||||
"G_0_URL = \"https://huggingface.co/datasets/ms903/sovits4.0-768vec-layer12/resolve/main/sovits_768l12_pre_large_320k/clean_G_320000.pth\" #@param [\"https://huggingface.co/datasets/ms903/sovits4.0-768vec-layer12/resolve/main/sovits_768l12_pre_large_320k/clean_G_320000.pth\", \"https://huggingface.co/1asbgdh/sovits4.0-volemb-vec768/resolve/main/clean_G_320000.pth\"] {allow-input: true}\n",
|
||||
"\n",
|
||||
"download_pretrained_diffusion_model = True #@param {type:\"boolean\"}\n",
|
||||
"diff_model_URL = \"https://huggingface.co/datasets/ms903/Diff-SVC-refactor-pre-trained-model/resolve/main/fix_pitch_add_vctk_600k/model_0.pt\" #@param {type:\"string\"}\n",
|
||||
|
@ -173,10 +173,14 @@
|
|||
"\n",
|
||||
"if download_pretrained_model:\n",
|
||||
" !curl -L {D_0_URL} -o logs/44k/D_0.pth\n",
|
||||
" !md5sum logs/44k/D_0.pth\n",
|
||||
" !curl -L {G_0_URL} -o logs/44k/G_0.pth\n",
|
||||
" !md5sum logs/44k/G_0.pth\n",
|
||||
"\n",
|
||||
"if download_pretrained_diffusion_model:\n",
|
||||
" !curl -L {diff_model_URL} -o logs/44k/diffusion/model_0.pt"
|
||||
" !mkdir -p logs/44k/diffusion\n",
|
||||
" !curl -L {diff_model_URL} -o logs/44k/diffusion/model_0.pt\n",
|
||||
" !md5sum logs/44k/diffusion/model_0.pt"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
@ -281,6 +285,8 @@
|
|||
"%cd /content/so-vits-svc\n",
|
||||
"\n",
|
||||
"speech_encoder = \"vec768l12\" #@param [\"vec768l12\", \"vec256l9\", \"hubertsoft\", \"whisper-ppg\", \"whisper-ppg-large\"]\n",
|
||||
"use_vol_aug = False #@param {type:\"boolean\"}\n",
|
||||
"vol_aug = \"--vol_aug\" if use_vol_aug else \"\"\n",
|
||||
"\n",
|
||||
"from pretrain.meta import download_dict\n",
|
||||
"download_dict = download_dict()\n",
|
||||
|
@ -291,8 +297,9 @@
|
|||
"import os\n",
|
||||
"if not os.path.exists(output):\n",
|
||||
" !curl -L {url} -o {output}\n",
|
||||
" !md5sum {output}\n",
|
||||
"\n",
|
||||
"!python preprocess_flist_config.py --speech_encoder={speech_encoder}"
|
||||
"!python preprocess_flist_config.py --speech_encoder={speech_encoder} {vol_aug}"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
@ -320,6 +327,7 @@
|
|||
" import os\n",
|
||||
" if not os.path.exists(\"./pretrain/nsf_hifigan/model\"):\n",
|
||||
" !curl -L https://github.com/openvpi/vocoders/releases/download/nsf-hifigan-v1/nsf_hifigan_20221211.zip -o nsf_hifigan_20221211.zip\n",
|
||||
" !md5sum nsf_hifigan_20221211.zip\n",
|
||||
" !unzip nsf_hifigan_20221211.zip\n",
|
||||
" !rm -rf pretrain/nsf_hifigan\n",
|
||||
" !mv -v nsf_hifigan pretrain\n",
|
||||
|
|
Loading…
Reference in New Issue