Hugging Face's logo

mlx-community
/
IndexTTS

Text-to-Speech
IndexTTS
Safetensors
MLX
indextts
Model card Files
xet
Community
IndexTTS
File size: 4,204 Bytes 
485c2ed
63e3a96
485c2ed
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
    "model_type": "indextts",
    "bigvgan": {
        "adam_b1": 0.8,
        "adam_b2": 0.99,
        "lr_decay": 0.999998,
        "seed": 1234,
        "resblock": "1",
        "upsample_rates": [
            4,
            4,
            4,
            4,
            2,
            2
        ],
        "upsample_kernel_sizes": [
            8,
            8,
            4,
            4,
            4,
            4
        ],
        "upsample_initial_channel": 1536,
        "resblock_kernel_sizes": [
            3,
            7,
            11
        ],
        "resblock_dilation_sizes": [
            [
                1,
                3,
                5
            ],
            [
                1,
                3,
                5
            ],
            [
                1,
                3,
                5
            ]
        ],
        "feat_upsample": false,
        "speaker_embedding_dim": 512,
        "cond_d_vector_in_each_upsampling_layer": true,
        "gpt_dim": 1024,
        "activation": "snakebeta",
        "snake_logscale": true,
        "use_cqtd_instead_of_mrd": true,
        "cqtd_filters": 128,
        "cqtd_max_filters": 1024,
        "cqtd_filters_scale": 1,
        "cqtd_dilations": [
            1,
            2,
            4
        ],
        "cqtd_hop_lengths": [
            512,
            256,
            256
        ],
        "cqtd_n_octaves": [
            9,
            9,
            9
        ],
        "cqtd_bins_per_octaves": [
            24,
            36,
            48
        ],
        "resolutions": [
            [
                1024,
                120,
                600
            ],
            [
                2048,
                240,
                1200
            ],
            [
                512,
                50,
                240
            ]
        ],
        "mpd_reshapes": [
            2,
            3,
            5,
            7,
            11
        ],
        "use_spectral_norm": false,
        "discriminator_channel_mult": 1,
        "use_multiscale_melloss": true,
        "lambda_melloss": 15,
        "clip_grad_norm": 1000,
        "segment_size": 16384,
        "num_mels": 100,
        "num_freq": 1025,
        "n_fft": 1024,
        "hop_size": 256,
        "win_size": 1024,
        "sampling_rate": 24000,
        "fmin": 0,
        "fmax": null,
        "fmax_for_loss": null,
        "mel_type": "pytorch",
        "num_workers": 2,
        "dist_config": {
            "dist_backend": "nccl",
            "dist_url": "tcp://localhost:54321",
            "world_size": 1
        }
    },
    "bigvgan_checkpoint": "bigvgan_generator.pth",
    "dataset": {
        "bpe_model": "checkpoints/bpe.model",
        "sample_rate": 24000,
        "squeeze": false,
        "mel": {
            "sample_rate": 24000,
            "n_fft": 1024,
            "hop_length": 256,
            "win_length": 1024,
            "n_mels": 100,
            "mel_fmin": 0,
            "normalize": false
        }
    },
    "dvae_checkpoint": "dvae.pth",
    "gpt": {
        "model_dim": 1024,
        "max_mel_tokens": 605,
        "max_text_tokens": 402,
        "heads": 16,
        "use_mel_codes_as_input": true,
        "mel_length_compression": 1024,
        "layers": 20,
        "number_text_tokens": 12000,
        "number_mel_codes": 8194,
        "start_mel_token": 8192,
        "stop_mel_token": 8193,
        "start_text_token": 0,
        "stop_text_token": 1,
        "train_solo_embeddings": false,
        "condition_type": "conformer_perceiver",
        "condition_module": {
            "output_size": 512,
            "linear_units": 2048,
            "attention_heads": 8,
            "num_blocks": 6,
            "input_layer": "conv2d2",
            "perceiver_mult": 2
        }
    },
    "gpt_checkpoint": "gpt.pth",
    "vqvae": {
        "channels": 100,
        "num_tokens": 8192,
        "hidden_dim": 512,
        "num_resnet_blocks": 3,
        "codebook_dim": 512,
        "num_layers": 2,
        "positional_dims": 1,
        "kernel_size": 3,
        "smooth_l1_loss": true,
        "use_transposed_convs": false
    }
}