MockingBird Docker & Self-Hosted Deployment

GitHub

Clone a voice in 5 seconds to generate arbitrary speech in real-time

36,897 stars Python Python 1 file · ~3,673 tokens #ai#deep-learning#pytorch#speech#text-to-speech#tts
RAW Compose
1. Pull Image (DOCKERHUB) docker pull library/mockingbird
2. Docker Run (1-Click Launch) docker run -d --name mockingbird -p 8080:8080 --restart always mockingbird:latest
3. Podman Run podman run -d --name mockingbird -p 8080:8080 --restart always mockingbird:latest
4. Skopeo Inspect (Zero-Pull Manifest) skopeo inspect docker://docker.io/library/mockingbird:latest
5. ORAS Pull (OCI Artifact) oras pull mockingbird:latest
6. Compose Deployment docker compose up -d
docker-compose.yml
Download .yml 
version: '3.8'

services:
  server:
    image: mockingbird:latest
    build: .
    volumes:
      - ./datasets:/datasets
      - ./synthesizer/saved_models:/workspace/synthesizer/saved_models
    environment:
      - DATASET_MIRROR=US
      - FORCE_RETRAIN=false
      - TRAIN_DATASETS=aidatatang_200zh magicdata aishell3 data_aishell
      - TRAIN_SKIP_EXISTING=true
    ports:
      - 8080:8080
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids: [ '0' ]
              capabilities: [ gpu ]