diff --git a/README.md b/README.md
index 235f00b..93b0196 100644
--- a/README.md
+++ b/README.md
@@ -527,8 +527,8 @@ Different Python applications have different requirements, some of those require
5) Once that process has completed, we now need to change from the `(base)` Conda Python environment, to our newly created `(alltalkenv)` Conda Python environment:
`conda activate alltalkenv`
Your prompt should now change from `(base) C:\myfiles\>` to `(alltalkenv) C:\myfiles\>`
-5) **If you are NOT using an Nvidia card and CUDA, skip to step 6** We will need to force PyTorch to install with CUDA. So perform the following:
`pip cache purge` (Will clear out all current copies of downloads that pip has)
`pip uninstall torch torchaudio` (Will uninstall the the current version of Torch and Torchaudio from the `(alltalkenv)` environment)
-You can now either install the CUDA 11.8 or 12.1 version of Torch and Torchaudio with **one** of the following
**CUDA 11.8** > `pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118`
**CUDA 12.1** > `pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121`
+5) **If you are NOT using an Nvidia card and CUDA, skip to step 6** We will need to force PyTorch to install with CUDA. So perform the following:
`pip cache purge` (Clear the current Pip cache)
`pip uninstall torch torchaudio` (Uninstall Torch and Torchaudio from the `alltalkenv` environment)
+You can now either install the CUDA 11.8 or 12.1 version of Torch and Torchaudio with **one** of the following
**CUDA 11.8** > `pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118`
**CUDA 12.1** > `pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121`
6) Install one of the two requirements files. Whichever one of the two is correct for your machine type:
**Nvidia graphics card machines** - `pip install -r requirements_nvidia.txt`