File size: 10,890 Bytes
c5ed230
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5854014
 
c5ed230
5854014
 
c5ed230
 
 
5854014
 
c5ed230
5854014
 
 
 
 
 
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
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
import re
import requests
import os
import random
import string
from requests_toolbelt.multipart.encoder import MultipartEncoder

abs_path = os.path.dirname(__file__)
base = "http://127.0.0.1:23456"


# 映射表
def voice_speakers():
    url = f"{base}/voice/speakers"

    res = requests.post(url=url)
    json = res.json()
    for i in json:
        print(i)
        for j in json[i]:
            print(j)
    return json


# 语音合成 voice vits
def voice_vits(text, id=0, format="wav", lang="auto", length=1, noise=0.667, noisew=0.8, max=50):
    fields = {
        "text": text,
        "id": str(id),
        "format": format,
        "lang": lang,
        "length": str(length),
        "noise": str(noise),
        "noisew": str(noisew),
        "max": str(max)
    }
    boundary = '----VoiceConversionFormBoundary' + ''.join(random.sample(string.ascii_letters + string.digits, 16))

    m = MultipartEncoder(fields=fields, boundary=boundary)
    headers = {"Content-Type": m.content_type}
    url = f"{base}/voice"

    res = requests.post(url=url, data=m, headers=headers)
    fname = re.findall("filename=(.+)", res.headers["Content-Disposition"])[0]
    path = f"{abs_path}/{fname}"

    with open(path, "wb") as f:
        f.write(res.content)
    print(path)
    return path


# 语音转换 hubert-vits
def voice_hubert_vits(upload_path, id, format="wav", length=1, noise=0.667, noisew=0.8):
    upload_name = os.path.basename(upload_path)
    upload_type = f'audio/{upload_name.split(".")[1]}'  # wav,ogg

    with open(upload_path, 'rb') as upload_file:
        fields = {
            "upload": (upload_name, upload_file, upload_type),
            "id": str(id),
            "format": format,
            "length": str(length),
            "noise": str(noise),
            "noisew": str(noisew),
        }
        boundary = '----VoiceConversionFormBoundary' + ''.join(random.sample(string.ascii_letters + string.digits, 16))

        m = MultipartEncoder(fields=fields, boundary=boundary)
        headers = {"Content-Type": m.content_type}
        url = f"{base}/voice/hubert-vits"

        res = requests.post(url=url, data=m, headers=headers)
    fname = re.findall("filename=(.+)", res.headers["Content-Disposition"])[0]
    path = f"{abs_path}/{fname}"

    with open(path, "wb") as f:
        f.write(res.content)
    print(path)
    return path


# 维度情感模型 w2v2-vits
def voice_w2v2_vits(text, id=0, format="wav", lang="auto", length=1, noise=0.667, noisew=0.8, max=50, emotion=0):
    fields = {
        "text": text,
        "id": str(id),
        "format": format,
        "lang": lang,
        "length": str(length),
        "noise": str(noise),
        "noisew": str(noisew),
        "max": str(max),
        "emotion": str(emotion)
    }
    boundary = '----VoiceConversionFormBoundary' + ''.join(random.sample(string.ascii_letters + string.digits, 16))

    m = MultipartEncoder(fields=fields, boundary=boundary)
    headers = {"Content-Type": m.content_type}
    url = f"{base}/voice/w2v2-vits"

    res = requests.post(url=url, data=m, headers=headers)
    fname = re.findall("filename=(.+)", res.headers["Content-Disposition"])[0]
    path = f"{abs_path}/{fname}"

    with open(path, "wb") as f:
        f.write(res.content)
    print(path)
    return path


# 语音转换 同VITS模型内角色之间的音色转换
def voice_conversion(upload_path, original_id, target_id):
    upload_name = os.path.basename(upload_path)
    upload_type = f'audio/{upload_name.split(".")[1]}'  # wav,ogg

    with open(upload_path, 'rb') as upload_file:
        fields = {
            "upload": (upload_name, upload_file, upload_type),
            "original_id": str(original_id),
            "target_id": str(target_id),
        }
        boundary = '----VoiceConversionFormBoundary' + ''.join(random.sample(string.ascii_letters + string.digits, 16))
        m = MultipartEncoder(fields=fields, boundary=boundary)

        headers = {"Content-Type": m.content_type}
        url = f"{base}/voice/conversion"

        res = requests.post(url=url, data=m, headers=headers)

    fname = re.findall("filename=(.+)", res.headers["Content-Disposition"])[0]
    path = f"{abs_path}/{fname}"

    with open(path, "wb") as f:
        f.write(res.content)
    print(path)
    return path


def voice_ssml(ssml):
    fields = {
        "ssml": ssml,
    }
    boundary = '----VoiceConversionFormBoundary' + ''.join(random.sample(string.ascii_letters + string.digits, 16))

    m = MultipartEncoder(fields=fields, boundary=boundary)
    headers = {"Content-Type": m.content_type}
    url = f"{base}/voice/ssml"

    res = requests.post(url=url, data=m, headers=headers)
    fname = re.findall("filename=(.+)", res.headers["Content-Disposition"])[0]
    path = f"{abs_path}/{fname}"

    with open(path, "wb") as f:
        f.write(res.content)
    print(path)
    return path


def voice_dimensional_emotion(upload_path):
    upload_name = os.path.basename(upload_path)
    upload_type = f'audio/{upload_name.split(".")[1]}'  # wav,ogg

    with open(upload_path, 'rb') as upload_file:
        fields = {
            "upload": (upload_name, upload_file, upload_type),
        }
        boundary = '----VoiceConversionFormBoundary' + ''.join(random.sample(string.ascii_letters + string.digits, 16))

        m = MultipartEncoder(fields=fields, boundary=boundary)
        headers = {"Content-Type": m.content_type}
        url = f"{base}/voice/dimension-emotion"

        res = requests.post(url=url, data=m, headers=headers)
    fname = re.findall("filename=(.+)", res.headers["Content-Disposition"])[0]
    path = f"{abs_path}/{fname}"

    with open(path, "wb") as f:
        f.write(res.content)
    print(path)
    return path


import time

# while 1:
#     text = input()
#     l = len(text)
#     time1 = time.time()
#     voice_vits(text)
#     time2 = time.time()
#     print(f"len:{l}耗时:{time2 - time1}")

# text = "你好"


# ssml = """
# <speak lang="zh" format="mp3" length="1.2">
#     <voice id="92" >这几天心里颇不宁静。</voice>
#     <voice id="125">今晚在院子里坐着乘凉,忽然想起日日走过的荷塘,在这满月的光里,总该另有一番样子吧。</voice>
#     <voice id="142">月亮渐渐地升高了,墙外马路上孩子们的欢笑,已经听不见了;</voice>
#     <voice id="98">妻在屋里拍着闰儿,迷迷糊糊地哼着眠歌。</voice>
#     <voice id="120">我悄悄地披了大衫,带上门出去。</voice><break time="2s"/>
#     <voice id="121">沿着荷塘,是一条曲折的小煤屑路。</voice>
#     <voice id="122">这是一条幽僻的路;白天也少人走,夜晚更加寂寞。</voice>
#     <voice id="123">荷塘四面,长着许多树,蓊蓊郁郁的。</voice>
#     <voice id="124">路的一旁,是些杨柳,和一些不知道名字的树。</voice>
#     <voice id="125">没有月光的晚上,这路上阴森森的,有些怕人。</voice>
#     <voice id="126">今晚却很好,虽然月光也还是淡淡的。</voice><break time="2s"/>
#     <voice id="127">路上只我一个人,背着手踱着。</voice>
#     <voice id="128">这一片天地好像是我的;我也像超出了平常的自己,到了另一个世界里。</voice>
#     <voice id="129">我爱热闹,也爱冷静;<break strength="x-weak"/>爱群居,也爱独处。</voice>
#     <voice id="130">像今晚上,一个人在这苍茫的月下,什么都可以想,什么都可以不想,便觉是个自由的人。</voice>
#     <voice id="131">白天里一定要做的事,一定要说的话,现在都可不理。</voice>
#     <voice id="132">这是独处的妙处,我且受用这无边的荷香月色好了。</voice>
# </speak>
# """
# ssml = """
# <speak lang="zh">
#     <voice id="92" length="1.4">这几天心里颇不宁静。今晚<break/>在院子里坐着乘凉,忽然想起<break/>日日走过的荷塘,在这满月的光里,总该另有一番样子吧。</voice>
#     <voice id="142" length="1.4">月亮渐渐地升高了,墙外马路上孩子们的欢笑,已经听不见了;</voice><break time="2s"/>
#     <voice id="0" length="1.4" model="w2v2-vits" lang="ja">こんにちは</voice>
# </speak>
# """
# ssml = """
# <speak lang="ja">
#     <voice id="142" length="1.4">こんにちは</voice>
#     <voice id="0" length="1.4" model="w2v2-vits" emotion="177">こんにちは</voice>
#     <voice id="0" length="1.4" model="w2v2-vits">こんにちは</voice>
# </speak>
# """
ssml = """
<speak lang="auto">
    <voice>这几天心里颇不宁静。</voice>
    <voice>今晚在院子里坐着乘凉,忽然想起日日走过的荷塘,在这满月的光里,总该另有一番样子吧。</voice>
    <voice>月亮渐渐地升高了,墙外马路上孩子们的欢笑,已经听不见了;</voice>
    <voice>妻在屋里拍着闰儿,迷迷糊糊地哼着眠歌。</voice>
    <voice>我悄悄地披了大衫,带上门出去。</voice><break time="2s"/>
    <voice>沿着荷塘,是一条曲折的小煤屑路。</voice>
    <voice>这是一条幽僻的路;白天也少人走,夜晚更加寂寞。</voice>
    <voice>荷塘四面,长着许多树,蓊蓊郁郁的。</voice>
    <voice>路的一旁,是些杨柳,和一些不知道名字的树。</voice>
    <voice>没有月光的晚上,这路上阴森森的,有些怕人。</voice>
    <voice>今晚却很好,虽然月光也还是淡淡的。</voice><break time="2s"/>
    <voice>路上只我一个人,背着手踱着。</voice>
    <voice>这一片天地好像是我的;我也像超出了平常的自己,到了另一个世界里。</voice>
    <voice>我爱热闹,也爱冷静;<break strength="x-weak"/>爱群居,也爱独处。</voice>
    <voice>像今晚上,一个人在这苍茫的月下,什么都可以想,什么都可以不想,便觉是个自由的人。</voice>
    <voice>白天里一定要做的事,一定要说的话,现在都可不理。</voice>
    <voice>这是独处的妙处,我且受用这无边的荷香月色好了。</voice>
</speak>
"""

text = """你知道1+1=几吗?我觉得1+1≠3"""

t1 = time.time()
# voice_conversion("H:/git/vits-simple-api/47fa127a-03ab-11ee-a4dc-e0d4e84af078.wav", 91, 93)
# voice_hubert_vits("H:/git/vits-simple-api/47fa127a-03ab-11ee-a4dc-e0d4e84af078.wav",0)
# voice_vits(text,format="wav",lang="zh")
# voice_w2v2_vits(text,emotion=111)
# os.system(voice_ssml(ssml))
os.system(voice_vits(text,id=126, format="wav", max=0,noise=0.33,noisew=0.4,lang="zh"))
# voice_dimensional_emotion("H:/git/vits-simple-api/47fa127a-03ab-11ee-a4dc-e0d4e84af078.wav")
t2 = time.time()
# print(f"len:{len(text)}耗时:{t2 - t1}")
# for i in range(10):
#     t1 = time.time()
#     voice_vits(text, format="wav", lang="zh")
#     t2 = time.time()
#     print(f"len:{len(text)}耗时:{t2 - t1}")