Hugging Face's logo

nonoJDWAOIDAWKDA
/
Amelia2_ft_StyleTTS2

Text-to-Speech
English
StyleTTS2
speech-synthesis
Model card Files Community
Amelia2_ft_StyleTTS2
File size: 2,698 Bytes 
509573b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "model_params": {
    "decoder": {
      "resblock_dilation_sizes": [
        [
          1,
          3,
          5
        ],
        [
          1,
          3,
          5
        ],
        [
          1,
          3,
          5
        ]
      ],
      "resblock_kernel_sizes": [
        3,
        7,
        11
      ],
      "type": "hifigan",
      "upsample_initial_channel": 512,
      "upsample_kernel_sizes": [
        20,
        10,
        6,
        4
      ],
      "upsample_rates": [
        10,
        5,
        3,
        2
      ]
    },
    "diffusion": {
      "dist": {
        "estimate_sigma_data": true,
        "mean": -3.0,
        "sigma_data": 0.2,
        "std": 1.0
      },
      "embedding_mask_proba": 0.1,
      "transformer": {
        "head_features": 64,
        "multiplier": 2,
        "num_heads": 8,
        "num_layers": 3
      }
    },
    "dim_in": 64,
    "dropout": 0.2,
    "hidden_dim": 512,
    "max_conv_dim": 512,
    "max_dur": 50,
    "multispeaker": false,
    "n_layer": 3,
    "n_mels": 80,
    "n_token": 178,
    "slm": {
      "hidden": 768,
      "initial_channel": 64,
      "model": "microsoft/wavlm-base-plus",
      "nlayers": 13,
      "sr": 16000
    },
    "style_dim": 128
  },
  "training_config": {
    "epochs": 10,
    "batch_size": 2,
    "max_len": 630,
    "optimizer": {
      "bert_lr": 1e-05,
      "ft_lr": 0.0001,
      "lr": 0.0001
    },
    "loss_params": {
      "diff_epoch": 0,
      "joint_epoch": 110,
      "lambda_F0": 1.0,
      "lambda_ce": 20.0,
      "lambda_diff": 1.0,
      "lambda_dur": 1.0,
      "lambda_gen": 1.0,
      "lambda_mel": 5.0,
      "lambda_mono": 1.0,
      "lambda_norm": 1.0,
      "lambda_s2s": 1.0,
      "lambda_slm": 1.0,
      "lambda_sty": 1.0
    }
  },
  "preprocess_params": {
    "spect_params": {
      "hop_length": 300,
      "n_fft": 2048,
      "win_length": 1200
    },
    "sr": 24000
  },
  "data_params": {
    "OOD_data": "Data/OOD_texts.txt",
    "min_length": 50,
    "root_path": "Data/wavs",
    "train_data": "Data/train_list.txt",
    "val_data": "Data/val_list.txt"
  },
  "model_state": {
    "epoch": 5,
    "iterations": 2472,
    "val_loss": 0.376327246427536
  },
  "training_metrics": {
    "train_loss": [],
    "val_loss": [
      18.0,
      30.0,
      30.0,
      44.0,
      33.0,
      21.0,
      17.0
    ],
    "dur_loss": [
      0.44,
      0.398,
      0.368,
      0.373,
      0.362,
      0.371,
      0.376
    ],
    "F0_loss": [
      2.865,
      2.754,
      2.769,
      2.916,
      2.745,
      2.811,
      2.793
    ],
    "epochs": [
      1,
      2,
      3,
      4,
      5,
      6,
      7
    ]
  }
}