#### ✨ 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)
**This project is fundamentally different from Vits. Vits is TTS and this project is SVC. TTS cannot be carried out in this project, and Vits cannot carry out SVC, and the two project models are not universal.**
The project was developed to allow the developers' favorite anime characters to sing, Anything involving real people is a departure from the intent of the developer.
This project is an open source, offline project, and all members of SvcDevelopTeam and all developers and maintainers of this project (hereinafter referred to as contributors) have no control over this project. The contributor of this project has never provided any organization or individual with any form of assistance, including but not limited to data set extraction, data set processing, computing support, training support, infering, etc. Contributors to the project do not and cannot know what users are using the project for. Therefore, all AI models and synthesized audio based on the training of this project have nothing to do with the contributors of this project. All problems arising therefrom shall be borne by the user.
This project is run completely offline and cannot collect any user information or obtain user input data. Therefore, contributors to this project are not aware of all user input and models and therefore are not responsible for any user input.
This project is only a framework project, which does not have the function of speech synthesis itself, and all the functions require the user to train the model themselves. Meanwhile, there is no model attached to this project, and any secondary distributed project has nothing to do with the contributors of this project
# Warning: Please solve the authorization problem of the dataset on your own. You shall be solely responsible for any problems caused by the use of non-authorized datasets for training and all consequences thereof.The repository and its maintainer, svc develop team, have nothing to do with the consequences!
1. This project is established for academic exchange purposes only and is intended for communication and learning purposes. It is not intended for production environments.
2. Any videos based on sovits that are published on video platforms must clearly indicate in the description that they are used for voice changing and specify the input source of the voice or audio, for example, using videos or audios published by others and separating the vocals as input source for conversion, which must provide clear original video or music links. If your own voice or other synthesized voices from other commercial vocal synthesis software are used as the input source for conversion, you must also explain it in the description.
3. You shall be solely responsible for any infringement problems caused by the input source. When using other commercial vocal synthesis software as input source, please ensure that you comply with the terms of use of the software. Note that many vocal synthesis engines clearly state in their terms of use that they cannot be used for input source conversion.
4. It is forbidden to use the project to engage in illegal activities, religious and political activities. The project developers firmly resist the above activities. If they do not agree with this article, the use of the project is prohibited.
5. Continuing to use this project is deemed as agreeing to the relevant provisions stated in this repository README. This repository README has the obligation to persuade, and is not responsible for any subsequent problems that may arise.
6. If you use this project for any other plan, please contact and inform the author of this repository in advance. Thank you very much.
The singing voice conversion model uses SoftVC content encoder to extract source audio speech features, then the vectors are directly fed into VITS instead of converting to a text based intermediate; thus the pitch and intonations are conserved. Additionally, the vocoder is changed to [NSF HiFiGAN](https://github.com/openvpi/DiffSinger/tree/refactor/modules/nsf_hifigan) to solve the problem of sound interruption.
- Feature input is changed to [Content Vec](https://github.com/auspicious3000/contentvec) Transformer output of 12 layer, And compatible with 4.0 branches.
- Update the shallow diffusion, you can use the shallow diffusion model to improve the sound quality.
- You can support the 4.0 model by modifying the config.json of the 4.0 model, adding the speech_encoder field to the Model field of config.json, see below for details
- download model at [medium.pt](https://openaipublic.azureedge.net/main/whisper/models/345ae4da62f9b3d59415adc60127b97c714f32e89e936602e85993674d08dcb1/medium.pt), the model fits `whisper-ppg`
- or download model at [large-v2.pt](https://openaipublic.azureedge.net/main/whisper/models/81f7c96c852ee8fc832187b0132e569d6c3065a3252ed18e56effd0b6a73e524/large-v2.pt), the model fits `whisper-ppg-large`
- download model at [chinese-hubert-large-fairseq-ckpt.pt](https://huggingface.co/TencentGameMate/chinese-hubert-large/resolve/main/chinese-hubert-large-fairseq-ckpt.pt)
- download model at [WavLM-Base+.pt](https://valle.blob.core.windows.net/share/wavlm/WavLM-Base+.pt?sv=2020-08-04&st=2023-03-01T07%3A51%3A05Z&se=2033-03-02T07%3A51%3A00Z&sr=c&sp=rl&sig=QJXmSJG9DbMKf48UDIU1MfzIro8HQOf3sqlNXiflY1I%3D), the model fits `wavlmbase+`
- Place it under the `pretrain` director
##### **7. If OnnxHubert/ContentVec as the encoder**
Diffusion model references [Diffusion-SVC](https://github.com/CNChTu/Diffusion-SVC) diffusion model. The pre-trained diffusion model is universal with the DDSP-SVC's. You can go to [Diffusion-SVC](https://github.com/CNChTu/Diffusion-SVC) to get the pre-trained diffusion model.
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.
If you are using the `NSF-HIFIGAN enhancer` or `shallow diffusion`, you will need to download the pre-trained NSF-HIFIGAN model, or not if you do not need it.
In general, only the `Minimum Interval` needs to be adjusted. For statement audio it usually remains default. For singing audio it can be adjusted to `100` or even `50`.
Although this project has the script resample.py for resampling, to mono and loudness matching, the default loudness matching is to match to 0db. This may cause damage to the sound quality. While python's loudness matching package pyloudnorm is unable to limit the level, this results in a burst. Therefore, it is suggested to consider using professional sound processing software such as `adobe audition` for loudness matching processing. If you have already used other software for loudness matching, run the command with the argument `--skip_loudnorm`:
After enabling loudness embedding, the trained model will match the loudness of the input source; otherwise, it will be the loudness of the training set.
#### You can modify some parameters in the generated config.json and diffusion.yaml
*`keep_ckpts`: Keep the last `keep_ckpts` models during training. Set to `0` will keep them all. Default is `3`.
*`all_in_mem`, `cache_all_data`: Load all dataset to RAM. It can be enabled when the disk IO of some platforms is too low and the system memory is **much larger** than your dataset.
*`batch_size`: The amount of data loaded to the GPU for a single training session can be adjusted to a size lower than the video memory capacity.
-`-lg` | `--linear_gradient`: The cross fade length of two audio slices in seconds. If there is a discontinuous voice after forced slicing, you can adjust this value. Otherwise, it is recommended to use the default value of 0.
-`-a` | `--auto_predict_f0`: automatic pitch prediction for voice conversion, do not enable this when converting songs as it can cause serious pitch issues.
-`-cm` | `--cluster_model_path`: Cluster model or feature retrieval index path, if there is no training cluster or feature retrieval, fill in at will.
-`-cr` | `--cluster_infer_ratio`: The proportion of clustering scheme or feature retrieval ranges from 0 to 1. If there is no training clustering model or feature retrieval, the default is 0.
-`-eh` | `--enhance`: Whether to use NSF_HIFIGAN enhancer, this option has certain effect on sound quality enhancement for some models with few training sets, but has negative effect on well-trained models, so it is turned off by default.
-`-shd` | `--shallow_diffusion`: Whether to use shallow diffusion, which can solve some electrical sound problems after use. This option is turned off by default. When this option is enabled, NSF_HIFIGAN intensifier will be disabled
-`-usm` | `--use_spk_mix`: whether to use dynamic voice/merge their role
-`-lea` | `--loudness_envelope_adjustment`：The input source loudness envelope replaces the output loudness envelope fusion ratio. The closer to 1, the more the output loudness envelope is used
-`-fr` | `--feature_retrieval`：Whether to use feature retrieval? If clustering model is used, it will be disabled, and cm and cr parameters will become the index path and mixing ratio of feature retrieval
-`-se` | `--second_encoding`：Secondary encoding, secondary coding of the original audio before shallow diffusion, mystery options, sometimes good, sometimes bad
If the results from the previous section are satisfactory, or if you didn't understand what is being discussed in the following section, you can skip it, and it won't affect the model usage. (These optional settings have a relatively small impact, and they may have some effect on certain specific data, but in most cases, the difference may not be noticeable.)
### Automatic f0 prediction
During the 4.0 model training, an f0 predictor is also trained, which can be used for automatic pitch prediction during voice conversion. However, if the effect is not good, manual pitch prediction can be used instead. But please do not enable this feature when converting singing voice as it may cause serious pitch shifting!
Introduction: The clustering scheme can reduce timbre leakage and make the trained model sound more like the target's timbre (although this effect is not very obvious), but using clustering alone will lower the model's clarity (the model may sound unclear). Therefore, this model adopts a fusion method to linearly control the proportion of clustering and non-clustering schemes. In other words, you can manually adjust the ratio between "sounding like the target's timbre" and "being clear and articulate" to find a suitable trade-off point.
The existing steps before clustering do not need to be changed. All you need to do is to train an additional clustering model, which has a relatively low training cost.
- Train on a machine with good CPU performance. According to my experience, it takes about 4 minutes to train each speaker on a Tencent Cloud machine with 6-core CPU.
- Execute `python cluster/train_cluster.py`. The output model will be saved in `logs/44k/kmeans_10000.pt`.
- Specify `cluster_model_path` in `inference_main.py`.
- Specify `cluster_infer_ratio` in `inference_main.py`, where `0` means not using clustering at all, `1` means only using clustering, and usually `0.5` is sufficient.
Introduction: As with the clustering scheme, the timbre leakage can be reduced, the character is slightly better than clustering, but it will reduce the reasoning speed, using the fusion method, can linearly control the proportion of feature retrieval and non-feature retrieval.
First, it needs to be executed after generating hubert and f0：
```shell
python train_index.py -c configs/config.json
```
The output of the model will be in `logs/44k/feature_and_index.pkl`
- Inference process：
- The `--feature_retrieval` needs to be formulated first, and the clustering mode automatically switches to the feature retrieval mode.
- Specify `cluster_model_path` in `inference_main.py`.
- Specify `cluster_infer_ratio` in `inference_main.py`, where `0` means not using feature retrieval at all, `1` means only using feature retrieval, and usually `0.5` is sufficient.
### [](https://colab.research.google.com/github/svc-develop-team/so-vits-svc/blob/4.1-Stable/sovits4_for_colab.ipynb) [sovits4_for_colab.ipynb](https://colab.research.google.com/github/svc-develop-team/so-vits-svc/blob/4.1-Stable/sovits4_for_colab.ipynb)
The generated model contains data that is needed for further training. If you confirm that the model is final and not be used in further training, it is safe to strip these data to get smaller file size (about 1/3).
**Refer to `webui.py` file for stable Timbre mixing of the gadget/lab feature.**
Introduction: This function can combine multiple sound models into one sound model (convex combination or linear combination of multiple model parameters) to create sound lines that do not exist in reality
**Note:**
1. This function only supports single-speaker models
2. If the multi-speaker model is forced to be used, it is necessary to ensure that the number of speakers in multiple models is the same, so that the voices under the same SpaekerID can be mixed
3. Ensure that the model fields in config.json of all models to be mixed are the same
4. The output hybrid model can use any config.json of the model to be synthesized, but the clustering model will not be used
5. When batch uploading models, it is best to put the models into a folder and upload them together after selecting them
6. It is suggested to adjust the mixing ratio between 0 and 100, or to other numbers, but unknown effects will occur in the linear combination mode
7. After mixing, the file named output.pth will be saved in the root directory of the project
8. Convex combination mode will perform Softmax to add the mix ratio to 1, while linear combination mode will not
### Dynamic timbre mixing
**Refer to the `spkmix.py` file for an introduction to dynamic timbre mixing**
The start time must be the same as the end time of the previous one. The first start time must be 0, and the last end time must be 1 (time ranges from 0 to 1).
- Modify `"NyaruTaffy"` in `path = "NyaruTaffy"` in [onnx_export.py](https://github.com/svc-develop-team/so-vits-svc/blob/4.0/onnx_export.py) to your project name, `path = "aziplayer"`（onnx_export_speaker_mix makes you can mix speaker's voice）
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.)
|[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) |
|[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)
|[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 |
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.
*Some members have not listed according to their personal wishes.*
