Update README.md

README.md

@@ -6,9 +6,10 @@ language:
 Models trained from [VITS-fast-fine-tuning](https://github.com/Plachtaa/VITS-fast-fine-tuning)
 - Three speakers: laoliang (老梁), specialweek, zhongli.
 - The model is trained on the C+J base model with 500 epochs.
-- Following the official instruction, we use a single long audio of laoliang (~5 minutes) with auxiliary data as training data.
+- During training, we use a single long audio of laoliang (~5 minutes) with auxiliary data as training data.
 - After downloading models, you need to move finetune_speaker.json and G_latest.pth to _/path/to/ VITS-fast-fine-tuning_.
-- Finally, you can run  your local gradio application via _python VC_inference.py --model_dir ./G_latest.pth --share True_
+- Following [the official instruction](https://github.com/Plachtaa/VITS-fast-fine-tuning/blob/main/LOCAL.md), install required libraries.
+- On inference, you can run your local gradio application via _python VC_inference.py --model_dir ./G_latest.pth --share True_
 
 ```bash
 VITS-fast-fine-tuning