speech-to-speech/docker-compose.yml at main · troed/speech-to-speech · 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
---
services:

  llama:
    image: ghcr.io/ggml-org/llama.cpp:server-cuda
    command:
      - -hf
      - ggml-org/gemma-4-E4B-it-GGUF
      - -np
      - "2"
      - -c
      - "65536"
      - -fa
      - "on"
      - --swa-full
      - --host
      - 0.0.0.0
      - --port
      - "8080"
    ports:
      - 8080:8080/tcp
    volumes:
      - ./cache/:/root/.cache/
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids: ['0']
              capabilities: [gpu]

  pipeline:
    depends_on:
      - llama
    build:
      context: .
      dockerfile: ${DOCKERFILE:-Dockerfile}
    command:
      - speech-to-speech
      - --mode
      - socket
      - --recv_host
      - 0.0.0.0
      - --send_host
      - 0.0.0.0
      - --llm_backend
      - responses-api
      - --model_name
      - ggml-org/gemma-4-E4B-it-GGUF
      - --responses_api_base_url
      - http://llama:8080/v1
      - --responses_api_api_key
      - ""
      - --init_chat_role
      - system
      - --init_chat_prompt
      - "You are a helpful assistant"
    expose:
      - 12345/tcp
      - 12346/tcp
    ports:
      - 12345:12345/tcp
      - 12346:12346/tcp
    volumes:
      - ./cache/:/root/.cache/
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids: ['0']
              capabilities: [gpu]