File size: 6,368 Bytes
28c720a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
import argparse
import base64
import wave

import ormsgpack
import pyaudio
import requests
from pydub import AudioSegment
from pydub.playback import play

from tools.commons import ServeReferenceAudio, ServeTTSRequest
from tools.file import audio_to_bytes, read_ref_text


def parse_args():

    parser = argparse.ArgumentParser(
        description="Send a WAV file and text to a server and receive synthesized audio."
    )

    parser.add_argument(
        "--url",
        "-u",
        type=str,
        default="http://127.0.0.1:8080/v1/tts",
        help="URL of the server",
    )
    parser.add_argument(
        "--text", "-t", type=str, required=True, help="Text to be synthesized"
    )
    parser.add_argument(
        "--reference_id",
        "-id",
        type=str,
        default=None,
        help="ID of the reference model o be used for the speech",
    )
    parser.add_argument(
        "--reference_audio",
        "-ra",
        type=str,
        nargs="+",
        default=None,
        help="Path to the WAV file",
    )
    parser.add_argument(
        "--reference_text",
        "-rt",
        type=str,
        nargs="+",
        default=None,
        help="Reference text for voice synthesis",
    )
    parser.add_argument(
        "--output",
        "-o",
        type=str,
        default="generated_audio",
        help="Output audio file name",
    )
    parser.add_argument(
        "--play",
        type=bool,
        default=True,
        help="Whether to play audio after receiving data",
    )
    parser.add_argument("--normalize", type=bool, default=True)
    parser.add_argument(
        "--format", type=str, choices=["wav", "mp3", "flac"], default="wav"
    )
    parser.add_argument("--mp3_bitrate", type=int, default=64)
    parser.add_argument("--opus_bitrate", type=int, default=-1000)
    parser.add_argument("--latency", type=str, default="normal", help="延迟选项")
    parser.add_argument(
        "--max_new_tokens",
        type=int,
        default=1024,
        help="Maximum new tokens to generate",
    )
    parser.add_argument(
        "--chunk_length", type=int, default=100, help="Chunk length for synthesis"
    )
    parser.add_argument(
        "--top_p", type=float, default=0.7, help="Top-p sampling for synthesis"
    )
    parser.add_argument(
        "--repetition_penalty",
        type=float,
        default=1.2,
        help="Repetition penalty for synthesis",
    )
    parser.add_argument(
        "--temperature", type=float, default=0.7, help="Temperature for sampling"
    )
    parser.add_argument(
        "--speaker", type=str, default=None, help="Speaker ID for voice synthesis"
    )
    parser.add_argument("--emotion", type=str, default=None, help="Speaker's Emotion")
    parser.add_argument(
        "--streaming", type=bool, default=False, help="Enable streaming response"
    )
    parser.add_argument(
        "--channels", type=int, default=1, help="Number of audio channels"
    )
    parser.add_argument("--rate", type=int, default=44100, help="Sample rate for audio")

    return parser.parse_args()


if __name__ == "__main__":

    args = parse_args()

    idstr: str | None = args.reference_id
    # priority: ref_id > [{text, audio},...]
    if idstr is None:
        ref_audios = args.reference_audio
        ref_texts = args.reference_text
        if ref_audios is None:
            byte_audios = []
        else:
            byte_audios = [audio_to_bytes(ref_audio) for ref_audio in ref_audios]
        if ref_texts is None:
            ref_texts = []
        else:
            ref_texts = [read_ref_text(ref_text) for ref_text in ref_texts]
    else:
        byte_audios = []
        ref_texts = []
        pass  # in api.py

    data = {
        "text": args.text,
        "references": [
            ServeReferenceAudio(audio=ref_audio, text=ref_text)
            for ref_text, ref_audio in zip(ref_texts, byte_audios)
        ],
        "reference_id": idstr,
        "normalize": args.normalize,
        "format": args.format,
        "mp3_bitrate": args.mp3_bitrate,
        "opus_bitrate": args.opus_bitrate,
        "max_new_tokens": args.max_new_tokens,
        "chunk_length": args.chunk_length,
        "top_p": args.top_p,
        "repetition_penalty": args.repetition_penalty,
        "temperature": args.temperature,
        "speaker": args.speaker,
        "emotion": args.emotion,
        "streaming": args.streaming,
    }

    pydantic_data = ServeTTSRequest(**data)

    response = requests.post(
        args.url,
        data=ormsgpack.packb(pydantic_data, option=ormsgpack.OPT_SERIALIZE_PYDANTIC),
        stream=args.streaming,
        headers={
            "authorization": "Bearer YOUR_API_KEY",
            "content-type": "application/msgpack",
        },
    )

    if response.status_code == 200:
        if args.streaming:
            p = pyaudio.PyAudio()
            audio_format = pyaudio.paInt16  # Assuming 16-bit PCM format
            stream = p.open(
                format=audio_format, channels=args.channels, rate=args.rate, output=True
            )

            wf = wave.open(f"{args.output}.wav", "wb")
            wf.setnchannels(args.channels)
            wf.setsampwidth(p.get_sample_size(audio_format))
            wf.setframerate(args.rate)

            stream_stopped_flag = False

            try:
                for chunk in response.iter_content(chunk_size=1024):
                    if chunk:
                        stream.write(chunk)
                        wf.writeframesraw(chunk)
                    else:
                        if not stream_stopped_flag:
                            stream.stop_stream()
                            stream_stopped_flag = True
            finally:
                stream.close()
                p.terminate()
                wf.close()
        else:
            audio_content = response.content
            audio_path = f"{args.output}.{args.format}"
            with open(audio_path, "wb") as audio_file:
                audio_file.write(audio_content)

            audio = AudioSegment.from_file(audio_path, format=args.format)
            if args.play:
                play(audio)
            print(f"Audio has been saved to '{audio_path}'.")
    else:
        print(f"Request failed with status code {response.status_code}")
        print(response.json())