File size: 5,310 Bytes
fb894d9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "cells": [
    {
      "cell_type": "markdown",
      "source": [
        "## MB-iSTFT-VITS2 inference"
      ],
      "metadata": {
        "id": "N0bhDfmXOBRy"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "%matplotlib inline\n",
        "import matplotlib.pyplot as plt\n",
        "import IPython.display as ipd\n",
        "import librosa\n",
        "\n",
        "import os\n",
        "import json\n",
        "import math\n",
        "\n",
        "import requests\n",
        "import torch\n",
        "from torch import nn\n",
        "from torch.nn import functional as F\n",
        "from torch.utils.data import DataLoader\n",
        "\n",
        "import commons\n",
        "import utils\n",
        "from data_utils import TextAudioLoader, TextAudioCollate, TextAudioSpeakerLoader, TextAudioSpeakerCollate\n",
        "from models import SynthesizerTrn\n",
        "from text.symbols import symbols\n",
        "from text import text_to_sequence\n",
        "import langdetect\n",
        "\n",
        "from scipy.io.wavfile import write\n",
        "import re"
      ],
      "metadata": {
        "id": "2GppsfIWTo7m"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "def get_text(text, hps):\n",
        "    text_norm = text_to_sequence(text, hps.data.text_cleaners)\n",
        "    if hps.data.add_blank:\n",
        "        text_norm = commons.intersperse(text_norm, 0)\n",
        "    text_norm = torch.LongTensor(text_norm)\n",
        "    return text_norm\n",
        "\n",
        "\n",
        "def langdetector(text):  # from PolyLangVITS\n",
        "    try:\n",
        "        lang = langdetect.detect(text).lower()\n",
        "        if lang == 'ko':\n",
        "            return f'[KO]{text}[KO]'\n",
        "        elif lang == 'ja':\n",
        "            return f'[JA]{text}[JA]'\n",
        "        elif lang == 'en':\n",
        "            return f'[EN]{text}[EN]'\n",
        "        elif lang == 'zh-cn':\n",
        "            return f'[ZH]{text}[ZH]'\n",
        "        else:\n",
        "            return text\n",
        "    except Exception as e:\n",
        "        return text\n",
        "\n",
        "\n",
        "def vcss(inputstr):\n",
        "    fltstr = re.sub(r\"[\\[\\]\\(\\)\\{\\}]\", \"\", inputstr)\n",
        "    fltstr = langdetector(fltstr)\n",
        "    stn_tst = get_text(fltstr, hps)\n",
        "\n",
        "    speed = 1\n",
        "    sid = 0\n",
        "    output_dir = 'output'\n",
        "    with torch.no_grad():\n",
        "        x_tst = stn_tst.cuda().unsqueeze(0)\n",
        "        x_tst_lengths = torch.LongTensor([stn_tst.size(0)]).cuda()\n",
        "        audio = net_g.infer(x_tst, x_tst_lengths, sid=sid, noise_scale=.667, noise_scale_w=0.8, length_scale=1 / speed)[0][\n",
        "                0, 0].data.cpu().float().numpy()\n",
        "\n",
        "    ipd.display(ipd.Audio(audio, rate=hps.data.sampling_rate, normalize=False))"
      ],
      "metadata": {
        "id": "v85aPkPtOA3m"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "hps = utils.get_hparams_from_file(\"./configs/mini_mb_istft_vits2_base.json\")\n",
        "\n",
        "if \"use_mel_posterior_encoder\" in hps.model.keys() and hps.model.use_mel_posterior_encoder == True:\n",
        "    print(\"Using mel posterior encoder for VITS2\")\n",
        "    posterior_channels = 80  # vits2\n",
        "    hps.data.use_mel_posterior_encoder = True\n",
        "else:\n",
        "    print(\"Using lin posterior encoder for VITS1\")\n",
        "    posterior_channels = hps.data.filter_length // 2 + 1\n",
        "    hps.data.use_mel_posterior_encoder = False\n",
        "\n",
        "net_g = SynthesizerTrn(\n",
        "    len(symbols),\n",
        "    posterior_channels,\n",
        "    hps.train.segment_size // hps.data.hop_length,\n",
        "    **hps.model).cuda()\n",
        "_ = net_g.eval()\n",
        "\n",
        "_ = utils.load_checkpoint(\"./models/G_2000.pth\", net_g, None)"
      ],
      "metadata": {
        "id": "S6J9zwzrTvBX"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# - text input\n",
        "input = \"I try to get the waiter's attention by blinking in morse code\"\n",
        "vcss(input)"
      ],
      "metadata": {
        "id": "T9nV74YBTx1h"
      },
      "execution_count": null,
      "outputs": []
    }
  ],
  "metadata": {
    "kernelspec": {
      "display_name": "MB-VITS",
      "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": "3.8.16"
    },
    "vscode": {
      "interpreter": {
        "hash": "9f16a3c86bbbd14c7fe4bf55d76086aa28175c5396da58b2a4368fac2eb85de4"
      }
    },
    "colab": {
      "provenance": []
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}