Jason-Lu commited on
Commit
5ca640c
β€’
1 Parent(s): 0b81f97

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -3
README.md CHANGED
@@ -7,10 +7,13 @@ Models trained from [VITS-fast-fine-tuning](https://github.com/Plachtaa/VITS-fas
7
  - Three speakers: laoliang (老撁), specialweek, zhongli.
8
  - The model is based on the C+J base model and trained on a single NVIDIA 3090 with 300 epochs. It takes about 4.5 hours in total.
9
  - During training, we use a single long audio of laoliang (~5 minutes) with auxiliary data as training data.
10
- - After downloading models, you need to move finetune_speaker.json and G_latest.pth to _/path/to/ VITS-fast-fine-tuning_.
11
- - Following [the official instruction](https://github.com/Plachtaa/VITS-fast-fine-tuning/blob/main/LOCAL.md), install required libraries.
12
- - On inference, you can run your local gradio application via _python VC_inference.py --model_dir ./G_latest.pth --share True_
13
 
 
 
 
 
 
 
14
  ```bash
15
  VITS-fast-fine-tuning
16
  β”œβ”€β”€β”€VC_inference.py
 
7
  - Three speakers: laoliang (老撁), specialweek, zhongli.
8
  - The model is based on the C+J base model and trained on a single NVIDIA 3090 with 300 epochs. It takes about 4.5 hours in total.
9
  - During training, we use a single long audio of laoliang (~5 minutes) with auxiliary data as training data.
 
 
 
10
 
11
+ How to run the model?
12
+ - Follow [the official instruction](https://github.com/Plachtaa/VITS-fast-fine-tuning/blob/main/LOCAL.md), install required libraries.
13
+ - Download models and move _finetune_speaker.json_ and _G_latest.pth_ to _/path/to/ VITS-fast-fine-tuning_.
14
+ - Run _python VC_inference.py --model_dir ./G_latest.pth --share True_ to start a local gradio inference demo.
15
+
16
+ File structure
17
  ```bash
18
  VITS-fast-fine-tuning
19
  β”œβ”€β”€β”€VC_inference.py