Add cpu ci

.github/workflows/build-and-push-to-ghcr.yml

@@ -93,3 +93,47 @@ jobs:
           cache-to: type=registry,ref=ghcr.io/coqui-ai/xtts-streaming-server:cache-latest-cuda121
           tags: ghcr.io/coqui-ai/xtts-streaming-server:latest-cuda121, ghcr.io/coqui-ai/xtts-streaming-server:main-cuda121-${{ github.sha }}
           #build-args:
+  build-and-push-to-ghcr-cpu:
+    runs-on: ubuntu-22.04
+    steps:
+      -
+        name: Checkout
+        uses: actions/checkout@v3
+
+      -
+        name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: 'Login to GitHub Container Registry'
+        run: |
+          set -xe
+          docker login --username ${{ github.actor }} --password ${{ secrets.GITHUB_TOKEN }} ghcr.io
+
+      - name: 'Remove cache'
+        run: | 
+          sudo rm -rf /usr/share/dotnet
+          sudo rm -rf /opt/ghc
+          sudo rm -rf "/usr/local/share/boost"
+          sudo rm -rf "$AGENT_TOOLSDIRECTORY"
+
+      - name: Build only for PR CPU
+        if: github.ref != 'refs/heads/main'
+        uses: docker/build-push-action@v5
+        with:
+          context: "{{defaultContext}}:server"
+          file: Dockerfile.cpu
+          push: false # Do not push image for PR
+          cache-from: type=registry,ref=ghcr.io/coqui-ai/xtts-streaming-server:cache-latest-cpu; type=registry,ref=ghcr.io/coqui-ai/xtts-streaming-server:cache-pr-cuda121-${{ github.event.number }}
+          cache-to: type=registry,ref=ghcr.io/coqui-ai/xtts-streaming-server:cache-pr-cpu-${{ github.event.number }}
+
+      - name: Build and Push image CPU
+        if: github.ref == 'refs/heads/main'
+        uses: docker/build-push-action@v5
+        with:
+          context: "{{defaultContext}}:server"
+          file: Dockerfile.cpu
+          push: true # Push if merged
+          cache-from: type=registry,ref=ghcr.io/coqui-ai/xtts-streaming-server:cache-latest-cpu
+          cache-to: type=registry,ref=ghcr.io/coqui-ai/xtts-streaming-server:cache-latest-cpu
+          tags: ghcr.io/coqui-ai/xtts-streaming-server:latest-cpu, ghcr.io/coqui-ai/xtts-streaming-server:main-cpu-${{ github.sha }}
+          #build-args:

README.md

@@ -1,70 +1,79 @@
 # XTTS streaming server
 
-## Running the server
+## 1) Run the server
 
-To run a pre-built container (CUDA 11.8):
+### 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
+```
+
+CUDA 11.8 (for older cards):
 
 ```bash
 $ docker run --gpus=all -e COQUI_TOS_AGREED=1 --rm -p 8000:80 ghcr.io/coqui-ai/xtts-streaming-server:latest
 ```
 
-CUDA 12.1 version (for newer cards) 
+CPU (not recommended):
+
 ```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 -e COQUI_TOS_AGREED=1 --rm -p 8000:80 ghcr.io/coqui-ai/xtts-streaming-server:latest-cpu
 ```
 
-Run with a custom XTTS v2 model (FT or previous versions):
+Run with a fine-tuned model:
+
+Make sure the model folder `/path/to/model/folder`  contains the following files:
+- `config.json`
+- `model.pth`
+- `vocab.json`
+
 ```bash
 $ 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`
 ```
 
 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).
+the terms of the [CPML license](https://coqui.ai/cpml). (Fine-tuned XTTS models also are under 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
 
-## Testing the server
+To build the Docker container Pytorch 2.1 and CUDA 11.8 :
 
-### Using the gradio demo
+`DOCKERFILE` may be `Dockerfile`, `Dockerfile.cpu`, `Dockerfile.cuda121`, or your own custom Dockerfile.
 
 ```bash
-$ python -m pip install -r test/requirements.txt
-$ python demo.py
+$ git clone [email protected]: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
 ```
 
-### Using the test script
+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))
 
-```bash
-$ cd test
-$ python -m pip install -r requirements.txt
-$ python test_streaming.py
-```
+## 2) Testing the running server
 
-## Building the container
+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.
 
-1. To build the Docker container Pytorch 2.1 and CUDA 11.8 :
+### Clone `xtts-streaming-server` if you haven't already
 
 ```bash
-$ cd server
-$ docker build -t xtts-stream .
+$ git clone [email protected]:coqui-ai/xtts-streaming-server.git
 ```
-For Pytorch 2.1 and CUDA 12.1 :
-```bash
-$ cd server
-docker build -t xtts-stream . -f Dockerfile.cuda121
-```
-2. Run the server container:
+
+### Using the gradio demo
 
 ```bash
-$ docker run --gpus all -e COQUI_TOS_AGREED=1 --rm -p 8000:80 xtts-stream
+$ cd xtts-streaming-server
+$ python -m pip install -r test/requirements.txt
+$ python demo.py
 ```
 
-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).
-
-
-Make sure the model folder contains the following files:
-- `config.json`
-- `model.pth`
-- `vocab.json`
+### Using the test script
 
+```bash
+$ cd xtts-streaming-server/test
+$ python -m pip install -r requirements.txt
+$ python test_streaming.py
+```