azalea/VITS-fast-fine-tuning
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Songting
2023-07-22 22:52:14 +08:00
committed by GitHub
parent 496dd8486a
commit 2262cb8212
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+3 -3
View File
@@ -29,12 +29,12 @@ Chinese only：(No running huggingface spaces) Author: [Wwwwhy230825](https://gi
## Fine-tuning
See [LOCAL.md](https://github.com/Plachtaa/VITS-fast-fine-tuning/blob/main/LOCAL.md) for local training guide.
Google Colab notebook is deprecated, please deploy this project locally.
Alternatively, you can perform fine-tuning on [Google Colab](https://colab.research.google.com/drive/1pn1xnFfdLK63gVXDwV4zCXfVeo8c-I-0?usp=sharing) (2023/7/18: This is under maintainace, do not use)
### How long does it take?
1. Install dependencies
2. Choose pretrained model to start.
1. Install dependencies (3 min)
2. Choose pretrained model to start. The detailed differences between them are described in [Colab Notebook](https://colab.research.google.com/drive/1pn1xnFfdLK63gVXDwV4zCXfVeo8c-I-0?usp=sharing)
3. Upload the voice samples of the characters you wish to add，see [DATA.MD](https://github.com/Plachtaa/VITS-fast-fine-tuning/blob/main/DATA_EN.MD) for detailed uploading options.
4. Start fine-tuning. Time taken varies from 20 minutes ~ 2 hours, depending on the number of voices you uploaded.