File size: 18,890 Bytes
d699cfc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
# flake8: noqa: E402
import gc
import os
import logging
import re_matching
from tools.sentence import split_by_language

logging.getLogger("numba").setLevel(logging.WARNING)
logging.getLogger("markdown_it").setLevel(logging.WARNING)
logging.getLogger("urllib3").setLevel(logging.WARNING)
logging.getLogger("matplotlib").setLevel(logging.WARNING)

logging.basicConfig(
    level=logging.INFO, format="| %(name)s | %(levelname)s | %(message)s"
)

logger = logging.getLogger(__name__)

import torch
import utils
from infer import infer, latest_version, get_net_g, infer_multilang
import gradio as gr
import webbrowser
import numpy as np
from config import config
from tools.translate import translate
import librosa

net_g = None

device = config.webui_config.device
if device == "mps":
    os.environ["PYTORCH_ENABLE_MPS_FALLBACK"] = "1"


def free_up_memory():
    # Prior inference run might have large variables not cleaned up due to exception during the run.
    # Free up as much memory as possible to allow this run to be successful.
    gc.collect()
    if torch.cuda.is_available():
        torch.cuda.empty_cache()


def generate_audio(

    slices,

    sdp_ratio,

    noise_scale,

    noise_scale_w,

    length_scale,

    speaker,

    language,

    reference_audio,

    emotion,

    style_text,

    style_weight,

    skip_start=False,

    skip_end=False,

):
    audio_list = []
    # silence = np.zeros(hps.data.sampling_rate // 2, dtype=np.int16)

    free_up_memory()

    with torch.no_grad():
        for idx, piece in enumerate(slices):
            skip_start = idx != 0
            skip_end = idx != len(slices) - 1
            audio = infer(
                piece,
                reference_audio=reference_audio,
                emotion=emotion,
                sdp_ratio=sdp_ratio,
                noise_scale=noise_scale,
                noise_scale_w=noise_scale_w,
                length_scale=length_scale,
                sid=speaker,
                language=language,
                hps=hps,
                net_g=net_g,
                device=device,
                skip_start=skip_start,
                skip_end=skip_end,
                style_text=style_text,
                style_weight=style_weight,
            )
            audio16bit = gr.processing_utils.convert_to_16_bit_wav(audio)
            audio_list.append(audio16bit)
    return audio_list


def generate_audio_multilang(

    slices,

    sdp_ratio,

    noise_scale,

    noise_scale_w,

    length_scale,

    speaker,

    language,

    reference_audio,

    emotion,

    skip_start=False,

    skip_end=False,

):
    audio_list = []
    # silence = np.zeros(hps.data.sampling_rate // 2, dtype=np.int16)

    free_up_memory()

    with torch.no_grad():
        for idx, piece in enumerate(slices):
            skip_start = idx != 0
            skip_end = idx != len(slices) - 1
            audio = infer_multilang(
                piece,
                reference_audio=reference_audio,
                emotion=emotion,
                sdp_ratio=sdp_ratio,
                noise_scale=noise_scale,
                noise_scale_w=noise_scale_w,
                length_scale=length_scale,
                sid=speaker,
                language=language[idx],
                hps=hps,
                net_g=net_g,
                device=device,
                skip_start=skip_start,
                skip_end=skip_end,
            )
            audio16bit = gr.processing_utils.convert_to_16_bit_wav(audio)
            audio_list.append(audio16bit)
    return audio_list


def tts_split(

    text: str,

    speaker,

    sdp_ratio,

    noise_scale,

    noise_scale_w,

    length_scale,

    language,

    cut_by_sent,

    interval_between_para,

    interval_between_sent,

    reference_audio,

    emotion,

    style_text,

    style_weight,

):
    while text.find("\n\n") != -1:
        text = text.replace("\n\n", "\n")
    text = text.replace("|", "")
    para_list = re_matching.cut_para(text)
    para_list = [p for p in para_list if p != ""]
    audio_list = []
    for p in para_list:
        if not cut_by_sent:
            audio_list += process_text(
                p,
                speaker,
                sdp_ratio,
                noise_scale,
                noise_scale_w,
                length_scale,
                language,
                reference_audio,
                emotion,
                style_text,
                style_weight,
            )
            silence = np.zeros((int)(44100 * interval_between_para), dtype=np.int16)
            audio_list.append(silence)
        else:
            audio_list_sent = []
            sent_list = re_matching.cut_sent(p)
            sent_list = [s for s in sent_list if s != ""]
            for s in sent_list:
                audio_list_sent += process_text(
                    s,
                    speaker,
                    sdp_ratio,
                    noise_scale,
                    noise_scale_w,
                    length_scale,
                    language,
                    reference_audio,
                    emotion,
                    style_text,
                    style_weight,
                )
                silence = np.zeros((int)(44100 * interval_between_sent))
                audio_list_sent.append(silence)
            if (interval_between_para - interval_between_sent) > 0:
                silence = np.zeros(
                    (int)(44100 * (interval_between_para - interval_between_sent))
                )
                audio_list_sent.append(silence)
            audio16bit = gr.processing_utils.convert_to_16_bit_wav(
                np.concatenate(audio_list_sent)
            )  # 对完整句子做音量归一
            audio_list.append(audio16bit)
    audio_concat = np.concatenate(audio_list)
    return ("Success", (hps.data.sampling_rate, audio_concat))


def process_mix(slice):
    _speaker = slice.pop()
    _text, _lang = [], []
    for lang, content in slice:
        content = content.split("|")
        content = [part for part in content if part != ""]
        if len(content) == 0:
            continue
        if len(_text) == 0:
            _text = [[part] for part in content]
            _lang = [[lang] for part in content]
        else:
            _text[-1].append(content[0])
            _lang[-1].append(lang)
            if len(content) > 1:
                _text += [[part] for part in content[1:]]
                _lang += [[lang] for part in content[1:]]
    return _text, _lang, _speaker


def process_auto(text):
    _text, _lang = [], []
    for slice in text.split("|"):
        if slice == "":
            continue
        temp_text, temp_lang = [], []
        sentences_list = split_by_language(slice, target_languages=["zh", "ja", "en"])
        for sentence, lang in sentences_list:
            if sentence == "":
                continue
            temp_text.append(sentence)
            if lang == "ja":
                lang = "jp"
            temp_lang.append(lang.upper())
        _text.append(temp_text)
        _lang.append(temp_lang)
    return _text, _lang


def process_text(

    text: str,

    speaker,

    sdp_ratio,

    noise_scale,

    noise_scale_w,

    length_scale,

    language,

    reference_audio,

    emotion,

    style_text=None,

    style_weight=0,

):
    audio_list = []
    if language == "mix":
        bool_valid, str_valid = re_matching.validate_text(text)
        if not bool_valid:
            return str_valid, (
                hps.data.sampling_rate,
                np.concatenate([np.zeros(hps.data.sampling_rate // 2)]),
            )
        for slice in re_matching.text_matching(text):
            _text, _lang, _speaker = process_mix(slice)
            if _speaker is None:
                continue
            print(f"Text: {_text}\nLang: {_lang}")
            audio_list.extend(
                generate_audio_multilang(
                    _text,
                    sdp_ratio,
                    noise_scale,
                    noise_scale_w,
                    length_scale,
                    _speaker,
                    _lang,
                    reference_audio,
                    emotion,
                )
            )
    elif language.lower() == "auto":
        _text, _lang = process_auto(text)
        print(f"Text: {_text}\nLang: {_lang}")
        audio_list.extend(
            generate_audio_multilang(
                _text,
                sdp_ratio,
                noise_scale,
                noise_scale_w,
                length_scale,
                speaker,
                _lang,
                reference_audio,
                emotion,
            )
        )
    else:
        audio_list.extend(
            generate_audio(
                text.split("|"),
                sdp_ratio,
                noise_scale,
                noise_scale_w,
                length_scale,
                speaker,
                language,
                reference_audio,
                emotion,
                style_text,
                style_weight,
            )
        )
    return audio_list


def tts_fn(

    text: str,

    speaker,

    sdp_ratio,

    noise_scale,

    noise_scale_w,

    length_scale,

    language,

    reference_audio,

    emotion,

    prompt_mode,

    style_text=None,

    style_weight=0,

):
    if style_text == "":
        style_text = None
    if prompt_mode == "Audio prompt":
        if reference_audio == None:
            return ("Invalid audio prompt", None)
        else:
            reference_audio = load_audio(reference_audio)[1]
    else:
        reference_audio = None

    audio_list = process_text(
        text,
        speaker,
        sdp_ratio,
        noise_scale,
        noise_scale_w,
        length_scale,
        language,
        reference_audio,
        emotion,
        style_text,
        style_weight,
    )

    audio_concat = np.concatenate(audio_list)
    return "Success", (hps.data.sampling_rate, audio_concat)


def format_utils(text, speaker):
    _text, _lang = process_auto(text)
    res = f"[{speaker}]"
    for lang_s, content_s in zip(_lang, _text):
        for lang, content in zip(lang_s, content_s):
            res += f"<{lang.lower()}>{content}"
        res += "|"
    return "mix", res[:-1]


def load_audio(path):
    audio, sr = librosa.load(path, 48000)
    # audio = librosa.resample(audio, 44100, 48000)
    return sr, audio


def gr_util(item):
    if item == "Text prompt":
        return {"visible": True, "__type__": "update"}, {
            "visible": False,
            "__type__": "update",
        }
    else:
        return {"visible": False, "__type__": "update"}, {
            "visible": True,
            "__type__": "update",
        }


if __name__ == "__main__":
    if config.webui_config.debug:
        logger.info("Enable DEBUG-LEVEL log")
        logging.basicConfig(level=logging.DEBUG)
    hps = utils.get_hparams_from_file(config.webui_config.config_path)
    # 若config.json中未指定版本则默认为最新版本
    version = hps.version if hasattr(hps, "version") else latest_version
    net_g = get_net_g(
        model_path=config.webui_config.model, version=version, device=device, hps=hps
    )
    speaker_ids = hps.data.spk2id
    speakers = list(speaker_ids.keys())
    languages = ["ZH", "JP", "EN", "mix", "auto"]
    with gr.Blocks() as app:
        with gr.Row():
            with gr.Column():
                text = gr.TextArea(
                    label="输入文本内容",
                    placeholder="""

                    如果你选择语言为\'mix\',必须按照格式输入,否则报错:

                        格式举例(zh是中文,jp是日语,不区分大小写;说话人举例:gongzi):

                         [说话人1]<zh>你好,こんにちは! <jp>こんにちは,世界。

                         [说话人2]<zh>你好吗?<jp>元気ですか?

                         [说话人3]<zh>谢谢。<jp>どういたしまして。

                         ...

                    另外,所有的语言选项都可以用'|'分割长段实现分句生成。

                    """,
                )
                trans = gr.Button("中翻日", variant="primary")
                slicer = gr.Button("快速切分", variant="primary")
                formatter = gr.Button("检测语言,并整理为 MIX 格式", variant="primary")
                speaker = gr.Dropdown(
                    choices=speakers, value=speakers[0], label="Speaker"
                )
                _ = gr.Markdown(
                    value="提示模式(Prompt mode):可选文字提示或音频提示,用于生成文字或音频指定风格的声音。\n",
                    visible=False,
                )
                prompt_mode = gr.Radio(
                    ["Text prompt", "Audio prompt"],
                    label="Prompt Mode",
                    value="Text prompt",
                    visible=False,
                )
                text_prompt = gr.Textbox(
                    label="Text prompt",
                    placeholder="用文字描述生成风格。如:Happy",
                    value="Happy",
                    visible=False,
                )
                audio_prompt = gr.Audio(
                    label="Audio prompt", type="filepath", visible=False
                )
                sdp_ratio = gr.Slider(
                    minimum=0, maximum=1, value=0.5, step=0.1, label="SDP Ratio"
                )
                noise_scale = gr.Slider(
                    minimum=0.1, maximum=2, value=0.6, step=0.1, label="Noise"
                )
                noise_scale_w = gr.Slider(
                    minimum=0.1, maximum=2, value=0.9, step=0.1, label="Noise_W"
                )
                length_scale = gr.Slider(
                    minimum=0.1, maximum=2, value=1.0, step=0.1, label="Length"
                )
                language = gr.Dropdown(
                    choices=languages, value=languages[0], label="Language"
                )
                btn = gr.Button("生成音频!", variant="primary")
            with gr.Column():
                with gr.Accordion("融合文本语义", open=False):
                    gr.Markdown(
                        value="使用辅助文本的语意来辅助生成对话(语言保持与主文本相同)\n\n"
                        "**注意**:不要使用**指令式文本**(如:开心),要使用**带有强烈情感的文本**(如:我好快乐!!!)\n\n"
                        "效果较不明确,留空即为不使用该功能"
                    )
                    style_text = gr.Textbox(label="辅助文本")
                    style_weight = gr.Slider(
                        minimum=0,
                        maximum=1,
                        value=0.7,
                        step=0.1,
                        label="Weight",
                        info="主文本和辅助文本的bert混合比率,0表示仅主文本,1表示仅辅助文本",
                    )
                with gr.Row():
                    with gr.Column():
                        interval_between_sent = gr.Slider(
                            minimum=0,
                            maximum=5,
                            value=0.2,
                            step=0.1,
                            label="句间停顿(秒),勾选按句切分才生效",
                        )
                        interval_between_para = gr.Slider(
                            minimum=0,
                            maximum=10,
                            value=1,
                            step=0.1,
                            label="段间停顿(秒),需要大于句间停顿才有效",
                        )
                        opt_cut_by_sent = gr.Checkbox(
                            label="按句切分    在按段落切分的基础上再按句子切分文本"
                        )
                        slicer = gr.Button("切分生成", variant="primary")
                text_output = gr.Textbox(label="状态信息")
                audio_output = gr.Audio(label="输出音频")
                # explain_image = gr.Image(
                #     label="参数解释信息",
                #     show_label=True,
                #     show_share_button=False,
                #     show_download_button=False,
                #     value=os.path.abspath("./img/参数说明.png"),
                # )
        btn.click(
            tts_fn,
            inputs=[
                text,
                speaker,
                sdp_ratio,
                noise_scale,
                noise_scale_w,
                length_scale,
                language,
                audio_prompt,
                text_prompt,
                prompt_mode,
                style_text,
                style_weight,
            ],
            outputs=[text_output, audio_output],
        )

        trans.click(
            translate,
            inputs=[text],
            outputs=[text],
        )
        slicer.click(
            tts_split,
            inputs=[
                text,
                speaker,
                sdp_ratio,
                noise_scale,
                noise_scale_w,
                length_scale,
                language,
                opt_cut_by_sent,
                interval_between_para,
                interval_between_sent,
                audio_prompt,
                text_prompt,
                style_text,
                style_weight,
            ],
            outputs=[text_output, audio_output],
        )

        prompt_mode.change(
            lambda x: gr_util(x),
            inputs=[prompt_mode],
            outputs=[text_prompt, audio_prompt],
        )

        audio_prompt.upload(
            lambda x: load_audio(x),
            inputs=[audio_prompt],
            outputs=[audio_prompt],
        )

        formatter.click(
            format_utils,
            inputs=[text, speaker],
            outputs=[language, text],
        )

    print("推理页面已开启!")
    webbrowser.open(f"http://127.0.0.1:{config.webui_config.port}")
    app.launch(share=config.webui_config.share, server_port=config.webui_config.port)