danvics/orpheus-fastapi
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

ROCm update

Browse source
This commit is contained in:
Alexander J. 2025-07-05 11:05:05 +10:00 committed by GitHub
parent 0391696552
commit 7bd4cfceef
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 4 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
README.md
View file

@ -8,6 +8,9 @@ High-performance Text-to-Speech server with OpenAI-compatible API, multilingual
## Changelog
**v1.3.1** (2025-07-05)
- 🐳 ROCm Docker implementation contributed by [@wizardeur](https://github.com/wizardeur) – many thanks for your contribution ❤️
**v1.3.0** (2025-04-18)
- 🌐 Added comprehensive multilingual support with 16 new voice actors across 7 languages
- 🗣️ New voice actors include:
@ -108,7 +111,7 @@ Orpheus-FastAPI/
### 🐳 Docker compose
The docker compose file orchestrates the Orpheus-FastAPI for audio and a llama.cpp inference server for the base model token generation. The GGUF model is downloaded with the model-init service.
There are two versions, one for machines that have access to GPU support `docker-compose-gpu.yaml` and one for CPU support only: `docker-compose-cpu.yaml`
There are three versions, two for machines that have access to GPU support `docker-compose-gpu.yaml`, `docker-compose-gpu-rocm.yml` and one for CPU support only: `docker-compose-cpu.yaml`
```bash
cp .env.example .env # Create your .env file from the example