Text-to-Speech
Transformers
English
Chinese
bert-vits2
female
style-bert-vits-jpextra
tts
bertvits2
japanese
Instructions to use Mofa-Xingche/girl-style-bert-vits2-JPExtra-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Mofa-Xingche/girl-style-bert-vits2-JPExtra-models with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="Mofa-Xingche/girl-style-bert-vits2-JPExtra-models")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Mofa-Xingche/girl-style-bert-vits2-JPExtra-models", dtype="auto") - Notebooks
- Google Colab
- Kaggle
File size: 3,141 Bytes
d208677 | 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 | {
"train": {
"log_interval": 200,
"eval_interval": 4000,
"seed": 42,
"epochs": 120,
"learning_rate": 0.0001,
"betas": [
0.8,
0.99
],
"eps": 1e-09,
"batch_size": 17,
"bf16_run": false,
"fp16_run": false,
"lr_decay": 0.99996,
"segment_size": 16384,
"init_lr_ratio": 1,
"warmup_epochs": 0,
"c_mel": 45,
"c_kl": 1.0,
"c_commit": 100,
"skip_optimizer": true,
"freeze_ZH_bert": false,
"freeze_JP_bert": false,
"freeze_EN_bert": false,
"freeze_emo": false,
"freeze_style": false
},
"data": {
"use_jp_extra": true,
"training_files": "",
"validation_files": "",
"max_wav_value": 32768.0,
"sampling_rate": 44100,
"filter_length": 2048,
"hop_length": 512,
"win_length": 2048,
"n_mel_channels": 128,
"mel_fmin": 0.0,
"mel_fmax": null,
"add_blank": true,
"n_speakers": 5,
"cleaned_text": true,
"spk2id": {
"NotAnime-JP-age20female-amazinGood": 0,
"NotAnime-JP-age20female-calmCloud": 1,
"NotAnime-JP-age20female-coolcute": 2,
"NotAnime-JP-age20female-fineCrystal": 3,
"NotAnime-JP-age20male-lightFire": 4
},
"num_styles": 25,
"style2id": {
"Neutral": 0,
"amazinGood(down)": 1,
"amazinGood(lol)": 2,
"amazinGood(onmygod)": 3,
"amazinGood(normal)": 4,
"calmCloud(lol)": 5,
"calmCloud(question)": 6,
"calmCloud(down)": 7,
"calmCloud(hate)": 8,
"calmCloud(ohmygod)": 9,
"calmCloud(normal)": 10,
"coolcute(onmygod)": 11,
"coolcute(normal)": 12,
"coolcute(fine)": 13,
"coolcute(sad)": 14,
"fineCrystal(fine)": 15,
"fineCrystal(ohmygod)": 16,
"fineCrystal(veryfine)": 17,
"fineCrystal(normal)": 18,
"fineCrystal(sad)": 19,
"lightFire(question)": 20,
"lightFire(hello)": 21,
"lightFire(normal)": 22,
"lightFire(strong)": 23,
"lightFire(lol)": 24
}
},
"model": {
"use_spk_conditioned_encoder": true,
"use_noise_scaled_mas": true,
"use_mel_posterior_encoder": false,
"use_duration_discriminator": false,
"use_wavlm_discriminator": true,
"inter_channels": 192,
"hidden_channels": 192,
"filter_channels": 768,
"n_heads": 2,
"n_layers": 6,
"kernel_size": 3,
"p_dropout": 0.1,
"resblock": "1",
"resblock_kernel_sizes": [
3,
7,
11
],
"resblock_dilation_sizes": [
[
1,
3,
5
],
[
1,
3,
5
],
[
1,
3,
5
]
],
"upsample_rates": [
8,
8,
2,
2,
2
],
"upsample_initial_channel": 512,
"upsample_kernel_sizes": [
16,
16,
8,
2,
2
],
"n_layers_q": 3,
"use_spectral_norm": false,
"gin_channels": 512,
"slm": {
"model": "./slm/wavlm-base-plus",
"sr": 16000,
"hidden": 768,
"nlayers": 13,
"initial_channel": 64
}
},
"version": "2.1-JP-Extra",
"model_name": "NotAnimeJPManySpeaker"
} |