diff --git a/README.md b/README.md
index 22050c3f..a14887da 100644
--- a/README.md
+++ b/README.md
@@ -79,7 +79,12 @@ The script is modified from `train_second.py` which uses DP, as DDP does not wor
 ```bash
 python train_finetune.py --config_path ./Configs/config_ft.yml
 ```
-Please make sure you have the LibriTTS checkpoint downloaded and unzipped under the folder. The default configuration `config_ft.yml` finetunes on LJSpeech with 1 hour of speech data (around 1k samples) for 50 epochs. This took about 4 hours to finish on four NVidia A100. The quality is slightly worse (similar to NaturalSpeech on LJSpeech) than LJSpeech model trained from scratch with 24 hours of speech data, which took around 2.5 days to finish on four A100. 
+Please make sure you have the LibriTTS checkpoint downloaded and unzipped under the folder. The default configuration `config_ft.yml` finetunes on LJSpeech with 1 hour of speech data (around 1k samples) for 50 epochs. This took about 4 hours to finish on four NVidia A100. The quality is slightly worse (similar to NaturalSpeech on LJSpeech) than LJSpeech model trained from scratch with 24 hours of speech data, which took around 2.5 days to finish on four A100. The samples can be found at [#65 (comment)](https://github.com/yl4579/StyleTTS2/discussions/65#discussioncomment-7668393).
+
+If you are using a **single GPU** (because the script doesn't work with DDP) and want to save training speed and VRAM, you can do (thank [@korakoe](https://github.com/korakoe) for making the script at [#100](https://github.com/yl4579/StyleTTS2/pull/100)):
+```bash
+accelerate launch --mixed_precision=fp16 --num_processes=1 train_finetune_accelerate.py --config_path ./Configs/config_ft.yml
+```
 
 [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yl4579/StyleTTS2/blob/main/Colab/StyleTTS2_Finetune_Demo.ipynb)