Hugging Face's logo

drbaph
/
LongCat-AudioDiT-3.5B-fp8

Text-to-Speech
Transformers
Safetensors
Chinese
English
audiodit
comfyui
Model card Files
xet
 Community
LongCat-AudioDiT-3.5B-fp8
File size: 2,469 Bytes
0690d4d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "dit_adaln_type": "global",
  "dit_adaln_use_text_cond": true,
  "dit_bias": true,
  "dit_cross_attn": true,
  "dit_cross_attn_norm": false,
  "dit_depth": 32,
  "dit_dim": 2560,
  "dit_dropout": 0.0,
  "dit_eps": 1e-06,
  "dit_ff_mult": 3.6,
  "dit_heads": 32,
  "dit_long_skip": true,
  "dit_qk_norm": true,
  "dit_text_conv": true,
  "dit_text_dim": 768,
  "dit_use_latent_condition": true,
  "latent_dim": 64,
  "latent_hop": 2048,
  "max_wav_duration": 60,
  "model_type": "audiodit",
  "repa_dit_layer": 8,
  "sampling_rate": 24000,
  "sigma": 0.0,
  "text_add_embed": true,
  "text_encoder_config": {
    "_name_or_path": "ArthurZ/umt5-base",
    "architectures": [
      "UMT5ForConditionalGeneration"
    ],
    "chunk_size_feed_forward": 0,
    "classifier_dropout": 0.0,
    "d_ff": 2048,
    "d_kv": 64,
    "d_model": 768,
    "decoder_start_token_id": 0,
    "dense_act_fn": "gelu_new",
    "dropout_rate": 0.1,
    "dtype": "float32",
    "eos_token_id": 1,
    "feed_forward_proj": "gated-gelu",
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_factor": 1.0,
    "is_decoder": false,
    "is_encoder_decoder": true,
    "is_gated_act": true,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_epsilon": 1e-06,
    "model_type": "umt5",
    "num_decoder_layers": 12,
    "num_heads": 12,
    "num_layers": 12,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_past": true,
    "pad_token_id": 0,
    "problem_type": null,
    "relative_attention_max_distance": 128,
    "relative_attention_num_buckets": 32,
    "return_dict": true,
    "scalable_attention": true,
    "tie_word_embeddings": true,
    "tokenizer_class": "T5Tokenizer",
    "use_cache": true,
    "vocab_size": 256384
  },
  "text_encoder_model": "google/umt5-base",
  "text_norm_feat": true,
  "transformers_version": "5.3.0",
  "vae_config": {
    "c_mults": [
      1,
      2,
      4,
      8,
      16
    ],
    "channels": 128,
    "downsample_shortcut": "averaging",
    "downsampling_ratio": 2048,
    "encoder_latent_dim": 128,
    "final_tanh": false,
    "in_channels": 1,
    "in_shortcut": "duplicating",
    "latent_dim": 64,
    "model_type": "audiodit_vae",
    "out_shortcut": "averaging",
    "sample_rate": 24000,
    "scale": 0.71,
    "strides": [
      2,
      4,
      4,
      8,
      8
    ],
    "upsample_shortcut": "duplicating",
    "use_snake": true
  }
}