Skip to content

Commit ee6e970

Browse files
committed
RMVPE Readme Updata
1 parent f808d8e commit ee6e970

File tree

3 files changed

+5
-2
lines changed

3 files changed

+5
-2
lines changed

README.md

+2-1
Original file line numberDiff line numberDiff line change
@@ -164,7 +164,7 @@ unzip -od pretrain/nsf_hifigan pretrain/nsf_hifigan_20221211.zip
164164

165165
If you are using the `rmvpe` F0 Predictor, you will need to download the pre-trained RMVPE model.
166166

167-
- download model at [rmvpe.pt](https://huggingface.co/datasets/ylzz1997/rmvpe_pretrain_model/resolve/main/rmvpe.pt)
167+
- download model at [rmvpe.pt](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/rmvpe.pt)
168168
- Place it under the `pretrain` directory
169169

170170
## 📊 Dataset Preparation
@@ -484,6 +484,7 @@ Note: For Hubert Onnx models, please use the models provided by MoeSS. Currently
484484
|[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) |
485485
|[8461329](https://ieeexplore.ieee.org/document/8461329) | Crepe (F0 Predictor) | Crepe: A Convolutional Representation for Pitch Estimation | [maxrmorrison/torchcrepe](https://github.com/maxrmorrison/torchcrepe) |
486486
|[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) |
487+
|[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) |
487488
|[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) |
488489
|[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)
489490
|[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)

README_zh_CN.md

+2-1
Original file line numberDiff line numberDiff line change
@@ -164,7 +164,7 @@ unzip -od pretrain/nsf_hifigan pretrain/nsf_hifigan_20221211.zip
164164

165165
如果使用`rmvpe`F0预测器的话,需要下载预训练的 RMVPE 模型
166166

167-
+ 下载模型 [rmvpe.pt](https://huggingface.co/datasets/ylzz1997/rmvpe_pretrain_model/resolve/main/rmvpe.pt)
167+
+ 下载模型 [rmvpe.pt](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/rmvpe.pt)
168168
+ 放在`pretrain`目录下
169169

170170

@@ -485,6 +485,7 @@ python compress_model.py -c="configs/config.json" -i="logs/44k/G_30400.pth" -o="
485485
|[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) |
486486
|[8461329](https://ieeexplore.ieee.org/document/8461329) | Crepe (F0 Predictor) | Crepe: A Convolutional Representation for Pitch Estimation | [maxrmorrison/torchcrepe](https://github.com/maxrmorrison/torchcrepe) |
487487
|[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) |
488+
|[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) |
488489
|[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) |
489490
|[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)
490491
|[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)

compress_model.py

+1
Original file line numberDiff line numberDiff line change
@@ -34,6 +34,7 @@ def removeOptimizer(config: str, input_model: str, ishalf: bool, output_model: s
3434
new_dict_g = copyStateDict(state_dict_g)
3535
keys = []
3636
for k, v in new_dict_g['model'].items():
37+
if "enc_q" in k: continue # noqa: E701
3738
keys.append(k)
3839

3940
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}

0 commit comments

Comments
 (0)