Hugging Face's logo

IndexTeam
/
IndexTTS-2

Safetensors
English
Model card Files
xet
Community
18
IndexTTS-2
File size: 2,882 Bytes 
3219752
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
dataset:
    bpe_model: 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

gpt:
    model_dim: 1280
    max_mel_tokens: 1815
    max_text_tokens: 600
    heads: 20
    use_mel_codes_as_input: true
    mel_length_compression: 1024
    layers: 24
    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
    emo_condition_module:
        output_size: 512
        linear_units: 1024
        attention_heads: 4
        num_blocks: 4
        input_layer: "conv2d2"
        perceiver_mult: 2

semantic_codec:
    codebook_size: 8192
    hidden_size: 1024
    codebook_dim: 8
    vocos_dim: 384
    vocos_intermediate_dim: 2048
    vocos_num_layers: 12

s2mel:
    preprocess_params:
        sr: 22050
        spect_params:
            n_fft: 1024
            win_length: 1024
            hop_length: 256
            n_mels: 80
            fmin: 0
            fmax: "None"

    dit_type: "DiT"
    reg_loss_type: "l1"
    style_encoder:
        dim: 192
    length_regulator:
        channels: 512
        is_discrete: false
        in_channels: 1024
        content_codebook_size: 2048
        sampling_ratios: [1, 1, 1, 1]
        vector_quantize: false
        n_codebooks: 1
        quantizer_dropout: 0.0
        f0_condition: false
        n_f0_bins: 512
    DiT:
        hidden_dim: 512
        num_heads: 8
        depth: 13
        class_dropout_prob: 0.1
        block_size: 8192
        in_channels: 80
        style_condition: true
        final_layer_type: 'wavenet'
        target: 'mel'
        content_dim: 512
        content_codebook_size: 1024
        content_type: 'discrete'
        f0_condition: false
        n_f0_bins: 512
        content_codebooks: 1
        is_causal: false
        long_skip_connection: true
        zero_prompt_speech_token: false
        time_as_token: false
        style_as_token: false
        uvit_skip_connection: true
        add_resblock_in_transformer: false
    wavenet:
        hidden_dim: 512
        num_layers: 8
        kernel_size: 5
        dilation_rate: 1
        p_dropout: 0.2
        style_condition: true

gpt_checkpoint: gpt.pth
w2v_stat: wav2vec2bert_stats.pt
s2mel_checkpoint: s2mel.pth
emo_matrix: feat2.pt 
spk_matrix: feat1.pt
emo_num: [3, 17, 2, 8, 4, 5, 10, 24]
qwen_emo_path: qwen0.6bemo4-merge/ 
vocoder:
    type: "bigvgan"
    name: "nvidia/bigvgan_v2_22khz_80band_256x"
version: 2.0