CosyVoice/runtime/python/fastapi/client.py at f26aacf8373674bdfa5e8577212881aa03021504 · FunAudioLLM/CosyVoice · 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
# Copyright (c) 2024 Alibaba Inc (authors: Xiang Lyu)
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#   http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import argparse
import logging
import requests
import torch
import torchaudio
import numpy as np


def main():
    url = "http://{}:{}/inference_{}".format(args.host, args.port, args.mode)
    if args.mode == 'sft':
        payload = {
            'tts_text': args.tts_text,
            'spk_id': args.spk_id
        }
        response = requests.request("GET", url, data=payload, stream=True)
    elif args.mode == 'zero_shot':
        payload = {
            'tts_text': args.tts_text,
            'prompt_text': args.prompt_text
        }
        files = [('prompt_wav', ('prompt_wav', open(args.prompt_wav, 'rb'), 'application/octet-stream'))]
        response = requests.request("GET", url, data=payload, files=files, stream=True)
    elif args.mode == 'cross_lingual':
        payload = {
            'tts_text': args.tts_text,
        }
        files = [('prompt_wav', ('prompt_wav', open(args.prompt_wav, 'rb'), 'application/octet-stream'))]
        response = requests.request("GET", url, data=payload, files=files, stream=True)
    elif args.mode == 'instruct':
        payload = {
            'tts_text': args.tts_text,
            'spk_id': args.spk_id,
            'instruct_text': args.instruct_text
        }
        response = requests.request("GET", url, data=payload, stream=True)
    else:
        # instruct2
        url = url + "_v2"
        payload = {
            'tts_text': args.tts_text,
            'instruct_text': args.instruct_text,
            'format': 'pcm'  # option
        }
        files = [('prompt_wav', ('prompt_wav', open(args.prompt_wav, 'rb'), 'application/octet-stream'))]
        response = requests.request("GET", url, data=payload, files=files, stream=True)
    tts_audio = b''
    for r in response.iter_content(chunk_size=16000):
        tts_audio += r
    tts_speech = torch.from_numpy(np.array(np.frombuffer(tts_audio, dtype=np.int16))).unsqueeze(dim=0)
    logging.info('save response to {}'.format(args.tts_wav))
    torchaudio.save(args.tts_wav, tts_speech, target_sr)
    logging.info('get response')


if __name__ == "__main__":
    parser = argparse.ArgumentParser()
    parser.add_argument('--host',
                        type=str,
                        default='0.0.0.0')
    parser.add_argument('--port',
                        type=int,
                        default='50000')
    parser.add_argument('--mode',
                        default='sft',
                        choices=['sft', 'zero_shot', 'cross_lingual', 'instruct', 'instruct2'],
                        help='request mode')
    parser.add_argument('--tts_text',
                        type=str,
                        default='你好，我是通义千问语音合成大模型，请问有什么可以帮您的吗？')
    parser.add_argument('--spk_id',
                        type=str,
                        default='中文女')
    parser.add_argument('--prompt_text',
                        type=str,
                        default='希望你以后能够做的比我还好呦。')
    parser.add_argument('--prompt_wav',
                        type=str,
                        default='../../../zero_shot_prompt.wav')
    parser.add_argument('--instruct_text',
                        type=str,
                        default='Theo \'Crimson\', is a fiery, passionate rebel leader. \
                                 Fights with fervor for justice, but struggles with impulsiveness.')
    parser.add_argument('--tts_wav',
                        type=str,
                        default='demo.wav')
    args = parser.parse_args()
    prompt_sr, target_sr = 16000, 22050
    main()