WindyMadman/so-vits-svc
1
0
Fork 0
mirror of https://github.com/svc-develop-team/so-vits-svc.git synced 2025-01-07 03:17:31 +08:00
Code Issues Packages Projects Releases Wiki Activity

RMVPE Readme Updata

Browse Source
This commit is contained in:
YuriHead 2023-07-13 00:22:22 +08:00
parent f808d8e60b
commit ee6e97057d
3 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
README.md
View File

@ -164,7 +164,7 @@ unzip -od pretrain/nsf_hifigan pretrain/nsf_hifigan_20221211.zip
If you are using the `rmvpe` F0 Predictor, you will need to download the pre-trained RMVPE model.
- download model at [rmvpe.pt](https://huggingface.co/datasets/ylzz1997/rmvpe_pretrain_model/resolve/main/rmvpe.pt)
- download model at [rmvpe.pt](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/rmvpe.pt)
- Place it under the `pretrain` directory
## 📊 Dataset Preparation
@ -484,6 +484,7 @@ Note: For Hubert Onnx models, please use the models provided by MoeSS. Currently
|[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) |
|[2306.15412v2](https://arxiv.org/abs/2306.15412v2) | RMVPE (F0 Predictor) | RMVPE: A Robust Model for Vocal Pitch Estimation in Polyphonic Music | [Dream-High/RMVPE](https://github.com/Dream-High/RMVPE) |
|[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)

3
README_zh_CN.md
View File

@ -164,7 +164,7 @@ unzip -od pretrain/nsf_hifigan pretrain/nsf_hifigan_20221211.zip
如果使用`rmvpe`F0预测器的话，需要下载预训练的 RMVPE 模型
+ 下载模型 [rmvpe.pt](https://huggingface.co/datasets/ylzz1997/rmvpe_pretrain_model/resolve/main/rmvpe.pt)
+ 下载模型 [rmvpe.pt](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/rmvpe.pt)
+ 放在`pretrain`目录下
@ -485,6 +485,7 @@ python compress_model.py -c="configs/config.json" -i="logs/44k/G_30400.pth" -o="
|[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) |
|[2306.15412v2](https://arxiv.org/abs/2306.15412v2) | RMVPE (F0 Predictor) | RMVPE: A Robust Model for Vocal Pitch Estimation in Polyphonic Music | [Dream-High/RMVPE](https://github.com/Dream-High/RMVPE) |
|[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)

1
compress_model.py
View File

@ -34,6 +34,7 @@ def removeOptimizer(config: str, input_model: str, ishalf: bool, output_model: s
new_dict_g = copyStateDict(state_dict_g)
keys = []
for k, v in new_dict_g['model'].items():
if "enc_q" in k: continue # noqa: E701
keys.append(k)
new_dict_g = {k: new_dict_g['model'][k].half() for k in keys} if ishalf else {k: new_dict_g['model'][k] for k in keys}