From f5836eca66f5c6185beae9be3b5b0f21c35c16f5 Mon Sep 17 00:00:00 2001
From: WeberJulian <julian.weber@hotmail.fr>
Date: Wed, 13 Dec 2023 12:07:26 +0100
Subject: [PATCH] Update readme

---
 README.md | 23 ++++++++++++++++-------
 1 file changed, 16 insertions(+), 7 deletions(-)

diff --git a/README.md b/README.md
index 48313ae..b525352 100644
--- a/README.md
+++ b/README.md
@@ -2,12 +2,12 @@
 
 ## 1) Run the server
 
-### Recommended: use a pre-built container
+### Use a pre-built image
 
 CUDA 12.1:
 
 ```bash
-$ docker run --gpus=all -e COQUI_TOS_AGREED=1 --rm -p 8000:80  ghcr.io/coqui-ai/xtts-streaming-server:latest-cuda121
+$ docker run --gpus=all -e COQUI_TOS_AGREED=1 --rm -p 8000:80 ghcr.io/coqui-ai/xtts-streaming-server:latest-cuda121
 ```
 
 CUDA 11.8 (for older cards):
@@ -16,6 +16,12 @@ CUDA 11.8 (for older cards):
 $ docker run --gpus=all -e COQUI_TOS_AGREED=1 --rm -p 8000:80 ghcr.io/coqui-ai/xtts-streaming-server:latest
 ```
 
+CPU (not recommended):
+
+```bash
+$ docker run -e COQUI_TOS_AGREED=1 --rm -p 8000:80 ghcr.io/coqui-ai/xtts-streaming-server:latest-cpu
+```
+
 Run with a fine-tuned model:
 
 Make sure the model folder `/path/to/model/folder`  contains the following files:
@@ -27,14 +33,18 @@ Make sure the model folder `/path/to/model/folder`  contains the following files
 $ docker run -v /path/to/model/folder:/app/tts_models --gpus=all -e COQUI_TOS_AGREED=1  --rm -p 8000:80 ghcr.io/coqui-ai/xtts-streaming-server:latest`
 ```
 
-## Not Recommended: Build the container yourself
+Setting the `COQUI_TOS_AGREED` environment variable to `1` indicates you have read and agreed to
+the terms of the [CPML license](https://coqui.ai/cpml). (Fine-tuned XTTS models also are under the [CPML license](https://coqui.ai/cpml))
+
+## Build the image yourself
 
 To build the Docker container Pytorch 2.1 and CUDA 11.8 :
 
 `DOCKERFILE` may be `Dockerfile`, `Dockerfile.cpu`, `Dockerfile.cuda121`, or your own custom Dockerfile.
 
 ```bash
-$ cd server
+$ git clone git@github.com:coqui-ai/xtts-streaming-server.git
+$ cd xtts-streaming-server/server
 $ docker build -t xtts-stream . -f DOCKERFILE
 $ docker run --gpus all -e COQUI_TOS_AGREED=1 --rm -p 8000:80 xtts-stream
 ```
@@ -46,7 +56,7 @@ the terms of the [CPML license](https://coqui.ai/cpml). (Fine-tuned XTTS models
 
 Once your Docker container is running, you can test that it's working properly. You will need to run the following code from a fresh terminal.
 
-### Clone `xtts-streaming-server`
+### Clone `xtts-streaming-server` if you haven't already
 
 ```bash
 $ git clone git@github.com:coqui-ai/xtts-streaming-server.git
@@ -63,8 +73,7 @@ $ python demo.py
 ### Using the test script
 
 ```bash
-$ cd xtts-streaming-server
-$ cd test
+$ cd xtts-streaming-server/test
 $ python -m pip install -r requirements.txt
 $ python test_streaming.py
 ```
\ No newline at end of file