diff --git a/README.md b/README.md
index e983c97..c304f8b 100644
--- a/README.md
+++ b/README.md
@@ -61,7 +61,7 @@ Try it on Colab: [![Open In Colab](https://colab.research.google.com/assets/cola
 
 1. Python >= 3.8 (Recommend >= 3.10)
 2. [**Install CUDA on your system.**](https://developer.nvidia.com/cuda-downloads).
-3. [**Install cuDNN v8 to your CUDA dir**](https://developer.nvidia.com/rdp/cudnn-archive) if you want to use **Faster-Whisper**.
+3. [**Install cuDNN to your CUDA dir**](https://developer.nvidia.com/cudnn-downloads) if you want to use **Faster-Whisper**.
 4. [**Install PyTorch (with CUDA) to your Python.**](https://pytorch.org/get-started/locally/)
 5. [**Create a Google API key**](https://aistudio.google.com/app/apikey) if you want to use **Gemini API** for translation. (Free 15 requests / minute)
 6. [**Create a OpenAI API key**](https://platform.openai.com/api-keys) if you want to use **Whisper API** for transcription or **GPT API** for translation.
diff --git a/README_CN.md b/README_CN.md
index f7a3634..179ff5b 100644
--- a/README_CN.md
+++ b/README_CN.md
@@ -59,7 +59,7 @@ flowchart LR
 
 1. Python >= 3.8 (推荐 >= 3.10)
 2. [**在您的系统上安装CUDA。**](https://developer.nvidia.com/cuda-downloads)
-3. 如果你想使用 **Faster-Whisper**, 需要[**将 cuDNN v8 安装到你的CUDA目录中**](https://developer.nvidia.com/rdp/cudnn-archive)。
+3. 如果你想使用 **Faster-Whisper**, 需要[**将 cuDNN 安装到你的CUDA目录中**](https://developer.nvidia.com/cudnn-downloads)。
 4. [**将PyTorch（带有CUDA）安装到您的Python中。**](https://pytorch.org/get-started/locally/)
 5. 如果你想用 **Gemini API** 进行翻译，需要[**创建一个Google API密钥**](https://aistudio.google.com/app/apikey)。（每分钟免费15次请求）
 6. 如果你想用 **Whisper API** 进行转录或 **GPT API** 进行翻译，需要[**创建一个OpenAI API密钥**](https://platform.openai.com/api-keys)