F5-TTS Docker & Self-Hosted Deployment

GitHub

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

15,411 stars Python Python 1 file · ~6,761 tokens
RAW Compose
1. Pull Image (DOCKERHUB) docker pull soar97/triton-f5-tts
2. Docker Run (1-Click Launch) docker run -d --name f5-tts -p 8000:8000 --restart always soar97/triton-f5-tts:24.12
3. Podman Run podman run -d --name f5-tts -p 8000:8000 --restart always soar97/triton-f5-tts:24.12
4. Skopeo Inspect (Zero-Pull Manifest) skopeo inspect docker://docker.io/soar97/triton-f5-tts:24.12
5. ORAS Pull (OCI Artifact) oras pull soar97/triton-f5-tts:24.12
6. Compose Deployment docker compose up -d
src/f5_tts/runtime/triton_trtllm/docker-compose.yml
Download .yml 
services:
  tts:
    image: soar97/triton-f5-tts:24.12
    shm_size: '1gb'
    ports:
      - "8000:8000"
      - "8001:8001"
      - "8002:8002"
    environment:
      - PYTHONIOENCODING=utf-8
      - MODEL_ID=${MODEL_ID}
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids: ['0']
              capabilities: [gpu]
    command: >
      /bin/bash -c "pip install vocos && rm -rf F5-TTS && git clone https://github.com/SWivid/F5-TTS.git && cd F5-TTS/src/f5_tts/runtime/triton_trtllm/ && bash run.sh 0 4 $MODEL"