diff --git a/README.md b/README.md
index d3ea6ac..e2fbba9 100644
--- a/README.md
+++ b/README.md
@@ -113,7 +113,7 @@ After completing the above steps, the dataset directory will contain the preproc
 
 * `keep_ckpts`: Keep the last `keep_ckpts` models during training. Set to `0` will keep them all. Default is `3`.
 
-* `all_in_mem`: Load all dataset to RAM. It can be enabled when the disk IO of some platforms is too low and the system memory is much larger than your dataset.
+* `all_in_mem`: Load all dataset to RAM. It can be enabled when the disk IO of some platforms is too low and the system memory is **much larger** than your dataset.
 
 ## 🏋️‍♀️ Training
 
diff --git a/README_zh_CN.md b/README_zh_CN.md
index 66738b2..9cbd020 100644
--- a/README_zh_CN.md
+++ b/README_zh_CN.md
@@ -113,7 +113,7 @@ python preprocess_hubert_f0.py
 
 * `keep_ckpts`：训练时保留最后几个模型，`0`为保留所有，默认只保留最后`3`个
 
-* `all_in_mem`：加载所有数据集到内存中，某些平台的硬盘IO过于低下、同时内存容量*远大于*数据集体积时可以启用
+* `all_in_mem`：加载所有数据集到内存中，某些平台的硬盘IO过于低下、同时内存容量 **远大于** 数据集体积时可以启用
 
 ## 🏋️‍♀️ 训练