LocalTranscriber/docker-compose.yml at main · JerrettDavis/LocalTranscriber · 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
130
131
132
133
134
135
136
137
138
139
services:
  # ==========================================================================
  # Web UI (default)
  # ==========================================================================
  web:
    build:
      context: .
      target: web
      args:
        VARIANT: cpu
    image: local-transcriber:web
    ports:
      - "8080:8080"
    volumes:
      - ./models:/app/models
      - ./output:/app/output
    environment:
      - ASPNETCORE_ENVIRONMENT=Development
      - OLLAMA_HOST=http://ollama:11434
    depends_on:
      - ollama

  # Web with CUDA GPU support
  web-cuda:
    build:
      context: .
      target: web
      args:
        VARIANT: cuda
    image: local-transcriber:web-cuda
    ports:
      - "8080:8080"
    volumes:
      - ./models:/app/models
      - ./output:/app/output
    environment:
      - ASPNETCORE_ENVIRONMENT=Development
      - OLLAMA_HOST=http://ollama:11434
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    depends_on:
      - ollama
    profiles:
      - cuda

  # ==========================================================================
  # Web Client (Blazor WASM - static site)
  # ==========================================================================
  web-client:
    build:
      context: .
      target: client
    image: local-transcriber:web-client
    ports:
      - "8081:80"
    profiles:
      - client

  # ==========================================================================
  # CLI (for batch processing)
  # ==========================================================================
  cli:
    build:
      context: .
      target: cli
      args:
        VARIANT: cpu
    image: local-transcriber:cli
    volumes:
      - ./models:/app/models
      - ./output:/app/output
      - ./input:/app/input
    environment:
      - OLLAMA_HOST=http://ollama:11434
    profiles:
      - cli

  cli-cuda:
    build:
      context: .
      target: cli
      args:
        VARIANT: cuda
    image: local-transcriber:cli-cuda
    volumes:
      - ./models:/app/models
      - ./output:/app/output
      - ./input:/app/input
    environment:
      - OLLAMA_HOST=http://ollama:11434
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    profiles:
      - cli-cuda

  # ==========================================================================
  # Ollama (local LLM for formatting)
  # ==========================================================================
  ollama:
    image: ollama/ollama:latest
    ports:
      - "11434:11434"
    volumes:
      - ollama-data:/root/.ollama
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:11434/api/tags"]
      interval: 30s
      timeout: 10s
      retries: 3

  ollama-cuda:
    image: ollama/ollama:latest
    ports:
      - "11434:11434"
    volumes:
      - ollama-data:/root/.ollama
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    profiles:
      - cuda
      - cli-cuda

volumes:
  ollama-data: