taco/glados-ladosp-tts
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update readme and workflow to use docker hub
Some checks failed
Build and Publish Docker Images / build-cpu (push) Failing after 2m4s
Details
Build and Publish Docker Images / build-rocm (push) Failing after 2m5s
Details
Build and Publish Docker Images / build-cuda (push) Failing after 2m6s
Details

Browse Source
This commit is contained in:
taco
2026-06-13 00:45:39 -06:00
parent 84c22609bd
commit 2db83d1817
3 changed files with 138 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
.gitea/workflows/build.yml
View File

@@ -14,12 +14,11 @@ jobs:
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
- name: Log in to Gitea Container Registry
- name: Log in to Docker Hub
uses: docker/login-action@v3
with:
registry: git.toomuchtaco.net
username: ${{ gitea.actor }}
password: ${{ secrets.PACKING_TOKEN }}
username: ${{ secrets.DOCKER_HUB_USERNAME }}
password: ${{ secrets.DOCKER_HUB_KEY }}
- name: Build and push CPU image
uses: docker/build-push-action@v6
@@ -28,8 +27,8 @@ jobs:
file: Dockerfile
push: true
tags: |
git.toomuchtaco.net/${{ gitea.repository }}:latest
git.toomuchtaco.net/${{ gitea.repository }}:cpu
${{ secrets.DOCKER_HUB_USERNAME }}/glados-ladosp-tts:latest
${{ secrets.DOCKER_HUB_USERNAME }}/glados-ladosp-tts:cpu
build-cuda:
runs-on: ubuntu-latest
@@ -40,12 +39,11 @@ jobs:
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
- name: Log in to Gitea Container Registry
- name: Log in to Docker Hub
uses: docker/login-action@v3
with:
registry: git.toomuchtaco.net
username: ${{ gitea.actor }}
password: ${{ secrets.PACKING_TOKEN }}
username: ${{ secrets.DOCKER_HUB_USERNAME }}
password: ${{ secrets.DOCKER_HUB_KEY }}
- name: Build and push CUDA image
uses: docker/build-push-action@v6
@@ -53,7 +51,7 @@ jobs:
context: .
file: Dockerfile.cuda
push: true
tags: git.toomuchtaco.net/${{ gitea.repository }}:cuda
tags: ${{ secrets.DOCKER_HUB_USERNAME }}/glados-ladosp-tts:cuda
build-rocm:
runs-on: ubuntu-latest
@@ -64,12 +62,11 @@ jobs:
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
- name: Log in to Gitea Container Registry
- name: Log in to Docker Hub
uses: docker/login-action@v3
with:
registry: git.toomuchtaco.net
username: ${{ gitea.actor }}
password: ${{ secrets.PACKING_TOKEN }}
username: ${{ secrets.DOCKER_HUB_USERNAME }}
password: ${{ secrets.DOCKER_HUB_KEY }}
- name: Build and push ROCm image
uses: docker/build-push-action@v6
@@ -77,4 +74,4 @@ jobs:
context: .
file: Dockerfile.rocm
push: true
tags: git.toomuchtaco.net/${{ gitea.repository }}:rocm
tags: ${{ secrets.DOCKER_HUB_USERNAME }}/glados-ladosp-tts:rocm

122
README.md Normal file
View File

@@ -0,0 +1,122 @@
# GLaDOS TTS Server
Wyoming protocol TTS server for the [Portal_GLaDOS_v1](https://huggingface.co/WarriorMama777/GLaDOS_TTS) voice model (Style-Bert-VITS2), designed for Home Assistant integration.
## Quick Start
### CPU
```yaml
services:
glados-tts:
image: xerotacovix/glados-ladosp-tts:cpu
container_name: glados-tts
ports:
- "10200:10200"
volumes:
- glados_model_cache:/data
environment:
- MODEL_DIR=/data
- URI=tcp://0.0.0.0:10200
- DEVICE=cpu
restart: unless-stopped
volumes:
glados_model_cache:
```
### CUDA (NVIDIA GPU)
```yaml
services:
glados-tts:
image: xerotacovix/glados-ladosp-tts:cuda
container_name: glados-tts
ports:
- "10200:10200"
volumes:
- glados_model_cache:/data
environment:
- MODEL_DIR=/data
- URI=tcp://0.0.0.0:10200
- DEVICE=cuda
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: 1
capabilities: [gpu]
restart: unless-stopped
volumes:
glados_model_cache:
```
### ROCm (AMD GPU)
```yaml
services:
glados-tts:
image: xerotacovix/glados-ladosp-tts:rocm
container_name: glados-tts
ports:
- "10200:10200"
volumes:
- glados_model_cache:/data
environment:
- MODEL_DIR=/data
- URI=tcp://0.0.0.0:10200
- DEVICE=rocm
devices:
- /dev/kfd
- /dev/dri
restart: unless-stopped
volumes:
glados_model_cache:
```
## Docker Compose (All Variants)
The included [`docker-compose.yaml`](docker-compose.yaml) defines all three services with non-conflicting host ports:
- CPU on `10201`
- CUDA on `10200`
- ROCm on `10202`
Run only the service you need:
```bash
docker compose up glados-tts-cpu # CPU only
docker compose up glados-tts-cuda # CUDA only
docker compose up glados-tts-rocm # ROCm only
```
## Home Assistant Integration
See the detailed guides for Wyoming protocol setup and configuration:
- [HOMEASSISTANT_INTEGRATION.md](HOMEASSISTANT_INTEGRATION.md)
For AMD ROCm-specific deployment notes and troubleshooting:
- [README-GlaDOS-TYS-Wyoming-and-ROCM.md](README-GlaDOS-TYS-Wyoming-and-ROCM.md)
## Model
The model is downloaded automatically from HuggingFace on first start:
- **Repository**: [WarriorMama777/GLaDOS_TTS](https://huggingface.co/WarriorMama777/GLaDOS_TTS)
- **Model**: `Portal_GLaDOS_v1` (Style-Bert-VITS2)
## Languages
The server auto-detects input language and loads the appropriate BERT model:
- English (`microsoft/deberta-v3-large`)
- Japanese (`ku-nlp/deberta-v2-large-japanese-char-wwm`)
- Chinese (`hfl/chinese-roberta-wwm-ext-large`)
## Ports
| Variant | Container Port | Default Host Port |
|---------|---------------|-------------------|
| CPU | 10200 | 10201 |
| CUDA | 10200 | 10200 |
| ROCm | 10200 | 10202 |

15
docker-compose.yaml
View File

@@ -1,9 +1,6 @@
services:
glados-tts-cpu:
build:
context: .
dockerfile: Dockerfile
image: glados-tts-wyoming:cpu
image: xerotacovix/glados-ladosp-tts:cpu
container_name: glados-tts-cpu
ports:
- "10201:10200"
@@ -16,10 +13,7 @@ services:
restart: unless-stopped
glados-tts-cuda:
build:
context: .
dockerfile: Dockerfile.cuda
image: glados-tts-wyoming:cuda
image: xerotacovix/glados-ladosp-tts:cuda
container_name: glados-tts-cuda
ports:
- "10200:10200"
@@ -39,10 +33,7 @@ services:
restart: unless-stopped
glados-tts-rocm:
build:
context: .
dockerfile: Dockerfile.rocm
image: glados-tts-wyoming:rocm
image: xerotacovix/glados-ladosp-tts:rocm
container_name: glados-tts-rocm
ports:
- "10202:10200"