Nofated095
/
so-vits-svc
mirror of https://github.com/svc-develop-team/so-vits-svc.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Compare commits

base: Nofated095:a2e0be5d7cec497e9cf212a25e2e0ff9223dcb00
Branches Tags
Nofated095:leng-yue-patch-1
Nofated095:4.1-Latest
Nofated095:4.1-Stable
Nofated095:feat-sovuefy-protocol
Nofated095:feat-rich-loguru
Nofated095:Mera-SVC-32k
Nofated095:Mera-SVC-48k
Nofated095:fix/rmvpe
Nofated095:main
Nofated095:Moe-SVC
Nofated095:Moe-SVC-V2
Nofated095:Fairseq-Hubert-Onnx-Export
Nofated095:Nyaru-SVC
...
compare: Nofated095:6a6e81932acd2877d771a180fdd0827030b2d61f
Branches Tags
Nofated095:leng-yue-patch-1
Nofated095:4.1-Latest
Nofated095:4.1-Stable
Nofated095:feat-sovuefy-protocol
Nofated095:feat-rich-loguru
Nofated095:Mera-SVC-32k
Nofated095:Mera-SVC-48k
Nofated095:fix/rmvpe
Nofated095:main
Nofated095:Moe-SVC
Nofated095:Moe-SVC-V2
Nofated095:Fairseq-Hubert-Onnx-Export
Nofated095:Nyaru-SVC

3 Commits
a2e0be5d7c ... 6a6e81932a

Author SHA1 Message Date
Miuzarte 6a6e81932a Update README.md 2023-03-13 20:06:10 +08:00
红血球AE3803 58865936d6
Merge pull request #17 from Kerushii/patch-1 
address issues
 2023-03-13 20:48:25 +09:00
Teresa 0d859e27fc
address issues 
https://github.com/StarStringStudio/so-vits-svc/issues/15
 2023-03-13 00:12:56 -07:00
2 changed files with 3 additions and 3 deletions
Show Stats Expand all files Collapse all files

4
README.md
View File

@ -17,7 +17,7 @@
## Model Introduction
The singing voice conversion model uses SoftVC content encoder to extract source audio speech features, and inputs them together with F0 into VITS instead of the original text input to achieve the effect of song conversion. At the same time, the vocoder is changed to [NSF HiFiGAN](https://github.com/openvpi/DiffSinger/tree/refactor/modules/nsf_hifigan) to solve the problem of sound interruption.
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.
### 4.0 Version Update Content
@ -145,7 +145,7 @@ The existing steps before clustering do not need to be changed. All you need to
- Specify "cluster_model_path" in inference_main.
- Specify "cluster_infer_ratio" in inference_main, where 0 means not using clustering at all, 1 means only using clustering, and usually 0.5 is sufficient.
### [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1kv-3y2DmZo0uya8pEr1xk7cSB-4e_Pct?usp=sharing) [sovits4 for colab.ipynb](https://colab.research.google.com/drive/1kv-3y2DmZo0uya8pEr1xk7cSB-4e_Pct?usp=sharing)
### [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1kv-3y2DmZo0uya8pEr1xk7cSB-4e_Pct?usp=sharing) [sovits4_for_colab.ipynb](https://colab.research.google.com/drive/1kv-3y2DmZo0uya8pEr1xk7cSB-4e_Pct?usp=sharing)
## Exporting to Onnx

2
README_zh_CN.md
View File

@ -142,7 +142,7 @@ python inference_main.py -m "logs/44k/G_30400.pth" -c "configs/config.json" -n "
+ inference_main中指定cluster_model_path
+ inference_main中指定cluster_infer_ratio，0为完全不使用聚类，1为只使用聚类，通常设置0.5即可
### [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1kv-3y2DmZo0uya8pEr1xk7cSB-4e_Pct?usp=sharing) [sovits4 for colab.ipynb](https://colab.research.google.com/drive/1kv-3y2DmZo0uya8pEr1xk7cSB-4e_Pct?usp=sharing)
### [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1kv-3y2DmZo0uya8pEr1xk7cSB-4e_Pct?usp=sharing) [sovits4_for_colab.ipynb](https://colab.research.google.com/drive/1kv-3y2DmZo0uya8pEr1xk7cSB-4e_Pct?usp=sharing)
## Onnx导出