File size: 14,277 Bytes
eefa761
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "b6ee1ede",
   "metadata": {},
   "source": [
    "## Voice Style Control Demo"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "b7f043ee",
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import torch\n",
    "from openvoice import se_extractor\n",
    "from openvoice.api import BaseSpeakerTTS, ToneColorConverter"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "15116b59",
   "metadata": {},
   "source": [
    "### Initialization"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "aacad912",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Loaded checkpoint 'checkpoints/base_speakers/EN/checkpoint.pth'\n",
      "missing/unexpected keys: [] []\n",
      "Loaded checkpoint 'checkpoints/converter/checkpoint.pth'\n",
      "missing/unexpected keys: [] []\n"
     ]
    }
   ],
   "source": [
    "ckpt_base = 'checkpoints/base_speakers/EN'\n",
    "ckpt_converter = 'checkpoints/converter'\n",
    "device=\"cuda:0\" if torch.cuda.is_available() else \"cpu\"\n",
    "output_dir = 'outputs'\n",
    "\n",
    "base_speaker_tts = BaseSpeakerTTS(f'{ckpt_base}/config.json', device=device)\n",
    "base_speaker_tts.load_ckpt(f'{ckpt_base}/checkpoint.pth')\n",
    "\n",
    "tone_color_converter = ToneColorConverter(f'{ckpt_converter}/config.json', device=device)\n",
    "tone_color_converter.load_ckpt(f'{ckpt_converter}/checkpoint.pth')\n",
    "\n",
    "os.makedirs(output_dir, exist_ok=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7f67740c",
   "metadata": {},
   "source": [
    "### Obtain Tone Color Embedding"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f8add279",
   "metadata": {},
   "source": [
    "The `source_se` is the tone color embedding of the base speaker. \n",
    "It is an average of multiple sentences generated by the base speaker. We directly provide the result here but\n",
    "the readers feel free to extract `source_se` by themselves."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "63ff6273",
   "metadata": {},
   "outputs": [],
   "source": [
    "source_se = torch.load(f'{ckpt_base}/en_default_se.pth').to(device)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4f71fcc3",
   "metadata": {},
   "source": [
    "The `reference_speaker.mp3` below points to the short audio clip of the reference whose voice we want to clone. We provide an example here. If you use your own reference speakers, please **make sure each speaker has a unique filename.** The `se_extractor` will save the `targeted_se` using the filename of the audio and **will not automatically overwrite.**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "55105eae",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "OpenVoice version: v1\n",
      "[(0.0, 19.278375)]\n",
      "after vad: dur = 19.27798185941043\n"
     ]
    }
   ],
   "source": [
    "reference_speaker = './resources/demo_speaker0.mp3' # This is the voice you want to clone\n",
    "target_se, audio_name = se_extractor.get_se(reference_speaker, tone_color_converter, target_dir='processed', vad=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a40284aa",
   "metadata": {},
   "source": [
    "### Inference"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "73dc1259",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " > Text splitted to sentences.\n",
      "This audio is generated by OpenVoice.\n",
      " > ===========================\n",
      "ðɪs ˈɑdiˌoʊ ɪz ˈdʒɛnəɹˌeɪtɪd baɪ ˈoʊpən vɔɪs.\n",
      " length:45\n",
      " length:45\n"
     ]
    }
   ],
   "source": [
    "save_path = f'{output_dir}/output_en_default.wav'\n",
    "\n",
    "# Run the base speaker tts\n",
    "text = \"This audio is generated by OpenVoice.\"\n",
    "src_path = f'{output_dir}/tmp.wav'\n",
    "base_speaker_tts.tts(text, src_path, speaker='default', language='English', speed=1.0)\n",
    "\n",
    "# Run the tone color converter\n",
    "encode_message = \"@MyShell\"\n",
    "tone_color_converter.convert(\n",
    "    audio_src_path=src_path, \n",
    "    src_se=source_se, \n",
    "    tgt_se=target_se, \n",
    "    output_path=save_path,\n",
    "    message=encode_message)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6e3ea28a",
   "metadata": {},
   "source": [
    "**Try with different styles and speed.** The style can be controlled by the `speaker` parameter in the `base_speaker_tts.tts` method. Available choices: friendly, cheerful, excited, sad, angry, terrified, shouting, whispering. Note that the tone color embedding need to be updated. The speed can be controlled by the `speed` parameter. Let's try whispering with speed 0.9."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "fd022d38",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " > Text splitted to sentences.\n",
      "This audio is generated by OpenVoice.\n",
      " > ===========================\n",
      "ðɪs ˈɑdiˌoʊ ɪz ˈdʒɛnəɹˌeɪtɪd baɪ ˈoʊpən vɔɪs.\n",
      " length:45\n",
      " length:45\n"
     ]
    }
   ],
   "source": [
    "source_se = torch.load(f'{ckpt_base}/en_style_se.pth').to(device)\n",
    "save_path = f'{output_dir}/output_whispering.wav'\n",
    "\n",
    "# Run the base speaker tts\n",
    "text = \"This audio is generated by OpenVoice.\"\n",
    "src_path = f'{output_dir}/tmp.wav'\n",
    "base_speaker_tts.tts(text, src_path, speaker='whispering', language='English', speed=0.9)\n",
    "\n",
    "# Run the tone color converter\n",
    "encode_message = \"@MyShell\"\n",
    "tone_color_converter.convert(\n",
    "    audio_src_path=src_path, \n",
    "    src_se=source_se, \n",
    "    tgt_se=target_se, \n",
    "    output_path=save_path,\n",
    "    message=encode_message)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5fcfc70b",
   "metadata": {},
   "source": [
    "**Try with different languages.** OpenVoice can achieve multi-lingual voice cloning by simply replace the base speaker. We provide an example with a Chinese base speaker here and we encourage the readers to try `demo_part2.ipynb` for a detailed demo."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "deff30a4-d430-4b4d-9772-b936f5b564c4",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Loaded checkpoint 'checkpoints/base_speakers/ZH/checkpoint.pth'\n",
      "missing/unexpected keys: [] []\n"
     ]
    }
   ],
   "source": [
    "ckpt_base = 'checkpoints/base_speakers/ZH'\n",
    "base_speaker_tts = BaseSpeakerTTS(f'{ckpt_base}/config.json', device=device)\n",
    "base_speaker_tts.load_ckpt(f'{ckpt_base}/checkpoint.pth')\n",
    "\n",
    "source_se = torch.load(f'{ckpt_base}/zh_default_se.pth').to(device)\n",
    "save_path = f'{output_dir}/output_chinese.wav'\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "a71d1387",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " > Text splitted to sentences.\n",
      "毛岛灰绣眼鸟(学名:Zosterops mauritianus)是一种绣眼鸟科绣眼鸟属的鸟类,\n",
      "属于毛里求斯岛上两种特有种绣眼鸟之一,\n",
      "另一种是更为稀少的毛里求斯绣眼鸟.\n",
      "上半身整体为灰色, 下半身为灰白色,\n",
      "臀部和腋羽是十分显眼的白色.\n",
      "这种鸟栖息于次生林、森林和花园中[1].\n",
      "它与留尼汪灰绣眼鸟亲缘关系很近,\n",
      "曾经被认为是同种, 统称为马斯克林绣眼鸟[2]\n",
      " > ===========================\n",
      "mɑʊ↑t⁼ɑʊ↓↑ xweɪ→ ʃjoʊ↓ jɛn↓↑niɑʊ↓↑( ʃɥɛ↑miŋ↑,ts⁼eɪ↓oʊ→ɛ↑sɹ↓tʰi↓i↓a↓oʊ→pʰi→ɛ↑sɹ↓ ɛ↑mu↓eɪ→joʊ→a↓aɪ↓tʰi↓aɪ↓eɪ→ən→joʊ→ɛ↑sɹ↓) s`ɹ`↓ i→ts`⁼ʊŋ↓↑ ʃjoʊ↓ jɛn↓↑niɑʊ↓↑kʰə→ ʃjoʊ↓ jɛn↓↑niɑʊ↓↑ s`u↓↑ t⁼ə niɑʊ↓↑leɪ↓,\n",
      " length:199\n",
      " length:197\n",
      "s`u↓↑ɥ↑ mɑʊ↑li↓↑tʃʰjoʊ↑sɹ→ t⁼ɑʊ↓↑s`ɑŋ↓ liɑŋ↓↑ts`⁼ʊŋ↓↑ tʰə↓joʊ↓↑ts`⁼ʊŋ↓↑ ʃjoʊ↓ jɛn↓↑niɑʊ↓↑ ts`⁼ɹ`→i→,\n",
      " length:100\n",
      " length:100\n",
      "liŋ↓ i→ts`⁼ʊŋ↓↑ s`ɹ`↓ k⁼əŋ↓weɪ↑ ʃi→s`ɑʊ↓↑ t⁼ə mɑʊ↑li↓↑tʃʰjoʊ↑sɹ→ ʃjoʊ↓ jɛn↓↑niɑʊ↓↑.\n",
      " length:83\n",
      " length:83\n",
      "s`ɑŋ↓p⁼an↓s`ən→ ts`⁼əŋ↓↑tʰi↓↑ weɪ↓ xweɪ→sə↓,  ʃja↓p⁼an↓s`ən→ weɪ↓ xweɪ→p⁼aɪ↑sə↓,\n",
      " length:80\n",
      " length:80\n",
      "tʰwən↑p⁼u↓ xə↑ iɛ↓ɥ↓↑ s`ɹ`↓ s`ɹ`↑fən→ ʃjɛn↓↑jɛn↓↑ t⁼ə p⁼aɪ↑sə↓.\n",
      " length:63\n",
      " length:63\n",
      "ts`⁼ə↓ts`⁼ʊŋ↓↑ niɑʊ↓↑ tʃʰi→ʃi→ ɥ↑ tsʰɹ↓s`əŋ→lin↑, sən→lin↑ xə↑ xwa→ɥæn↑ ts`⁼ʊŋ→[ i→].\n",
      " length:85\n",
      " length:83\n",
      "tʰa→ ɥ↓↑ ljoʊ↑ni↑uɑŋ→ xweɪ→ ʃjoʊ↓ jɛn↓↑niɑʊ↓↑ tʃʰin→ɥæn↑ k⁼wan→ʃi↓ xən↓↑tʃ⁼in↓,\n",
      " length:79\n",
      " length:79\n",
      "tsʰəŋ↑tʃ⁼iŋ→ p⁼eɪ↓ ɹ`ən↓weɪ↑ s`ɹ`↓ tʰʊŋ↑ts`⁼ʊŋ↓↑,  tʰʊŋ↓↑ts`ʰəŋ→ weɪ↓ ma↓↑sɹ→kʰə↓lin↑ ʃjoʊ↓ jɛn↓↑niɑʊ↓↑[ əɹ`↓].\n",
      " length:111\n",
      " length:109\n"
     ]
    },
    {
     "ename": "TypeError",
     "evalue": "unsupported operand type(s) for -: 'builtin_function_or_method' and 'float'",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[30], line 20\u001b[0m\n\u001b[1;32m     18\u001b[0m \u001b[38;5;66;03m# 记录结束时间\u001b[39;00m\n\u001b[1;32m     19\u001b[0m end_time \u001b[38;5;241m=\u001b[39m time\u001b[38;5;241m.\u001b[39mtime\n\u001b[0;32m---> 20\u001b[0m execution_time \u001b[38;5;241m=\u001b[39m \u001b[43mend_time\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m-\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mstart_time\u001b[49m\n\u001b[1;32m     21\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m代码执行时间: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mexecution_time\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m 秒\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
      "\u001b[0;31mTypeError\u001b[0m: unsupported operand type(s) for -: 'builtin_function_or_method' and 'float'"
     ]
    }
   ],
   "source": [
    "import time\n",
    "\n",
    "# 记录开始时间\n",
    "start_time = time.time()\n",
    "# Run the base speaker tts\n",
    "text = \"毛岛灰绣眼鸟(学名:Zosterops mauritianus)是一种绣眼鸟科绣眼鸟属的鸟类,属于毛里求斯岛上两种特有种绣眼鸟之一,另一种是更为稀少的毛里求斯绣眼鸟。上半身整体为灰色,下半身为灰白色,臀部和腋羽是十分显眼的白色。这种鸟栖息于次生林、森林和花园中[1]。它与留尼汪灰绣眼鸟亲缘关系很近,曾经被认为是同种,统称为马斯克林绣眼鸟[2]\"\n",
    "src_path = f'{output_dir}/tmp.wav'\n",
    "base_speaker_tts.tts(text, src_path, speaker='default', language='Chinese', speed=1.0)\n",
    "\n",
    "# Run the tone color converter\n",
    "encode_message = \"@MyShell\"\n",
    "tone_color_converter.convert(\n",
    "    audio_src_path=src_path, \n",
    "    src_se=source_se, \n",
    "    tgt_se=target_se, \n",
    "    output_path=save_path,\n",
    "    message=encode_message)\n",
    "# 记录结束时间\n",
    "end_time = time.time\n",
    "execution_time = end_time - start_time\n",
    "print(f\"代码执行时间: {execution_time} 秒\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8e513094",
   "metadata": {},
   "source": [
    "**Tech for good.** For people who will deploy OpenVoice for public usage: We offer you the option to add watermark to avoid potential misuse. Please see the ToneColorConverter class. **MyShell reserves the ability to detect whether an audio is generated by OpenVoice**, no matter whether the watermark is added or not."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9628ffa1-1d60-4d1b-a9ed-619add064ebd",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "377f4b72-dfca-4c58-8a5c-fea056538cc2",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "31bf81ab-bac9-4996-8f47-8651052d713a",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "32a84a29-9515-4aaa-b4ad-3a530e8259f0",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "abd802ad-93ac-4db2-9ee5-0ad78b54e09e",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "interpreter": {
   "hash": "9d70c38e1c0b038dbdffdaa4f8bfa1f6767c43760905c87a9fbe7800d18c6c35"
  },
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.19"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}