Kimi-Audio/infer.py at master · xiaoyi1734/Kimi-Audio · 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
from kimia_infer.api.kimia import KimiAudio
import os
import soundfile as sf
import argparse

if __name__ == "__main__":
    parser = argparse.ArgumentParser()
    parser.add_argument("--model_path", type=str, default="moonshotai/Kimi-Audio-7B-Instruct")
    args = parser.parse_args()

    model = KimiAudio(
        model_path=args.model_path,
        load_detokenizer=True,
    )

    sampling_params = {
        "audio_temperature": 0.8,
        "audio_top_k": 10,
        "text_temperature": 0.0,
        "text_top_k": 5,
        "audio_repetition_penalty": 1.0,
        "audio_repetition_window_size": 64,
        "text_repetition_penalty": 1.0,
        "text_repetition_window_size": 16,
    }

    messages = [
        {"role": "user", "message_type": "text", "content": "请将音频内容转换为文字。"},
        {
            "role": "user",
            "message_type": "audio",
            "content": "test_audios/asr_example.wav",
        },
    ]

    wav, text = model.generate(messages, **sampling_params, output_type="text")
    print(">>> output text: ", text)

    output_dir = "test_audios/output"
    os.makedirs(output_dir, exist_ok=True)
    # audio2audio
    messages = [
        {
            "role": "user",
            "message_type": "audio",
            "content": "test_audios/qa_example.wav",
        }
    ]

    wav, text = model.generate(messages, **sampling_params, output_type="both")
    sf.write(
        os.path.join(output_dir, "output.wav"),
        wav.detach().cpu().view(-1).numpy(),
        24000,
    )
    print(">>> output text: ", text)


    # audio2audio multiturn
    messages = [
        {
            "role": "user",
            "message_type": "audio",
            "content": "test_audios/multiturn/case1/multiturn_q1.wav",
        },
        {
            "role": "assistant",
            "message_type": "audio-text",
            "content": ["test_audios/multiturn/case1/multiturn_a1.wav", "当然可以，李白的诗很多，比如这句：“床前明月光，疑是地上霜。举头望明月，低头思故乡。"]
        },
        {
            "role": "user",
            "message_type": "audio",
            "content": "test_audios/multiturn/case1/multiturn_q2.wav",
        }
    ]
    wav, text = model.generate(messages, **sampling_params, output_type="both")
    sf.write(
        os.path.join(output_dir, "case_1_multiturn_a2.wav"),
        wav.detach().cpu().view(-1).numpy(),
        24000,
    )
    print(">>> output text: ", text)


    messages = [
        {
            "role": "user",
            "message_type": "audio",
            "content": "test_audios/multiturn/case2/multiturn_q1.wav",
        },
        {
            "role": "assistant",
            "message_type": "audio-text",
            "content": ["test_audios/multiturn/case2/multiturn_a1.wav", "当然可以，这很简单。一二三四五六七八九十。"]
        },
        {
            "role": "user",
            "message_type": "audio",
            "content": "test_audios/multiturn/case2/multiturn_q2.wav",
        }
    ]
    wav, text = model.generate(messages, **sampling_params, output_type="both")
    sf.write(
        os.path.join(output_dir, "case_2_multiturn_a2.wav"),
        wav.detach().cpu().view(-1).numpy(),
        24000,
    )
    print(">>> output text: ", text)