Uzbek_TTS/docker-compose.yml at latest_branch · nek1987/Uzbek_TTS · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
# Docker Compose for Uzbek TTS API
# Optimized for Coolify deployment with NVIDIA A40 GPU

version: '3.8'

services:
  uzbek-tts:
    build:
      context: .
      dockerfile: Dockerfile
    container_name: uzbek-tts-api
    restart: unless-stopped

    # GPU Configuration for NVIDIA A40
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids: ['0']  # Use first GPU (A40)
              capabilities: [gpu]

    # Environment Variables
    environment:
      # Application
      - APP_NAME=Uzbek TTS API
      - APP_VERSION=1.0.0
      - DEBUG=false

      # Server
      - HOST=0.0.0.0
      - PORT=8000
      - WORKERS=1

      # Model Paths
      - MODEL_PATH=/app/models/UZ.safetensors
      - VOCAB_PATH=/app/config/uz_vocab.txt
      - CONFIG_PATH=/app/config/UZTTS_conf.yaml

      # GPU Configuration (A40 Optimized)
      - DEVICE=cuda
      - NUM_WORKERS=6
      - ENABLE_TF32=true
      - ENABLE_COMPILE=true
      - CUDA_VISIBLE_DEVICES=0

      # Inference Configuration (Speed/Quality Balance)
      - NFE_STEPS=18
      - CFG_STRENGTH=1.5
      - TARGET_RMS=0.1
      - DEFAULT_SPEED=1.0

      # Cache Configuration
      - CACHE_SIZE=1000
      - CACHE_DIR=/app/cache
      - ENABLE_CACHE=true

      # Queue Configuration
      - MAX_QUEUE_SIZE=50
      - QUEUE_TIMEOUT=300

      # API Limits
      - MAX_TEXT_LENGTH=5000
      - MAX_AUDIO_DURATION=300
      - MAX_BATCH_SIZE=8

      # Monitoring
      - ENABLE_METRICS=true
      - METRICS_PORT=9090

      # Logging
      - LOG_LEVEL=INFO
      - LOG_DIR=/app/logs

      # Upload
      - UPLOAD_DIR=/app/uploads
      - MAX_UPLOAD_SIZE=10485760

      # CORS
      - CORS_ORIGINS=["*"]

    # Ports
    ports:
      - "8000:8000"  # API port
      - "9090:9090"  # Metrics port (optional)

    # Volumes
    volumes:
      # Models (persistent)
      - ./models:/app/models:rw
      # Config (read-only)
      - ./config:/app/config:ro
      # Cache (persistent)
      - ./cache:/app/cache:rw
      # Logs (persistent)
      - ./logs:/app/logs:rw
      # Uploads (persistent)
      - ./uploads:/app/uploads:rw

    # Health Check
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 60s

    # Logging
    logging:
      driver: "json-file"
      options:
        max-size: "10m"
        max-file: "3"

    # Network
    networks:
      - tts-network

# Networks
networks:
  tts-network:
    driver: bridge

# Volumes (optional, for named volumes instead of bind mounts)
# volumes:
#   models-data:
#   cache-data:
#   logs-data:
#   uploads-data: