Update README.md

README.md

@@ -85,30 +85,41 @@ It improves the quality of the lip-sync videos generated by the [Wav2Lip tool](h
 
 1. Install [python 3.10.11](https://www.python.org/downloads/release/python-31011/)
 2. Install [git](https://git-scm.com/downloads)
-3. Check python and git installation
+3. Install [Cuda 11.8](https://developer.nvidia.com/cuda-11-8-0-download-archive) if not ever done.
+  ![Illustration](demo/cuda.png)
+4. Check python and git installation
     ```bash
     python --version
     git --version
+    nvcc --version
     ```
    Must return something like
     ```bash
     Python 3.10.11
     git version 2.35.1.windows.2
+    nvcc: NVIDIA (R) Cuda compiler driver
+    Copyright (c) 2005-2022 NVIDIA Corporation
+    Built on Wed_Sep_21_10:41:10_Pacific_Daylight_Time_2022
+    Cuda compilation tools, release 11.8, V11.8.89
+    Build cuda_11.8.r11.8/compiler.31833905_0
     ```
-4. Install [Visual Studio](https://visualstudio.microsoft.com/fr/downloads/). During the install, make sure to include the Python and C++ packages in visual studio installer.
+5. Install [Visual Studio](https://visualstudio.microsoft.com/fr/downloads/). During the install, make sure to include the Python and C++ packages in visual studio installer.
    ![Illustration](demo/visual_studio_1.png)
    ![Illustration](demo/visual_studio_2.png)
-5. if you have multiple Python version on your computer edit wav2lip-studio.bat and change the following line:
+6. if you have multiple Python version on your computer edit wav2lip-studio.bat and change the following line:
     ```bash
     REM set PYTHON="your python.exe path"
     ```
-   ```bash
+    ```bash
     set PYTHON="your python.exe path"
     ```
-6. pyannote.audio:You need to agree to share your contact information to access pyannote models. 
-To do so, go to [pyannote diarization-3.1 huggingface repository](https://huggingface.co/pyannote/speaker-diarization-3.1) AND [pyannote segmentation-3.0 huggingface repository](https://huggingface.co/pyannote/segmentation-3.0) set each field and click "Agree and access repository"
+7. pyannote.audio:You need to agree to share your contact information to access pyannote models. 
+To do so, go to :
+    - [pyannote diarization-3.1 huggingface repository](https://huggingface.co/pyannote/speaker-diarization-3.1)
+    - [pyannote segmentation-3.0 huggingface repository](https://huggingface.co/pyannote/segmentation-3.0)
+set each field and click "Agree and access repository"
 ![Illustration](demo/hf_aggrement.png)
-7. Create an access token to Huggingface:
+9. Create an access token to Huggingface:
     1. Connect with your account
     2. go to [access tokens](https://huggingface.co/settings/token) in settings
     3. create a new token in read mode
@@ -119,7 +130,7 @@ To do so, go to [pyannote diarization-3.1 huggingface repository](https://huggin
        "huggingface_token": "your token"
      }
      ```
-8. double click on wav2lip-studio.bat, that will install the requirements and download the models 
+10. double click on wav2lip-studio.bat, that will install the requirements and download models
 
 ## Tutorial
 - [FR version](https://youtu.be/43Q8YASkcUA)