Hugging Face's logo

seifwaked
/
xttsv2Core

xtts
custom_code
Model card Files Community
xttsv2Core
File size: 2,487 Bytes 
62078e1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "model_type": "xtts",
  "architectures": [
    "XttsGPT"
  ],
  "audio_config": {
    "fmax": 8000,
    "fmin": 0,
    "hop_length": 256,
    "mel_channels": 80,
    "mel_norms_file": null,
    "n_fft": 1024,
    "output_sample_rate": 24000,
    "power": 1.0,
    "sample_rate": 22050,
    "win_length": 1024
  },
  "d_vector_dim": 512,
  "decoder_input_dim": 1024,
  "num_chars": 255,
  "duration_const": 102400,
  "output_hop_length": 256,
  "input_sample_rate": 22050,
  "output_sample_rate": 24000,
  "gpt": {
    "model_type": "xtts_gpt"
  },
  "gpt_config": {
    "model_type": "xtts_gpt",
    "architectures": [
      "XttsGPT"
    ],
    "vocab_size": 6681,
    "hidden_size": 1024,
    "num_hidden_layers": 30,
    "num_attention_heads": 16,
    "n_inner": 4096,
    "number_text_tokens": 6681,
    "num_audio_tokens": 1026,
    "max_audio_tokens": 605,
    "start_audio_token": 1024,
    "stop_audio_token": 1025,
    "max_text_tokens": 402,
    "max_prompt_tokens": 70,
    "activation_function": "gelu_new",
    "attn_pdrop": 0.1,
    "layer_norm_epsilon": 1e-05,
    "initializer_range": 0.02,
    "use_masking_gt_prompt_approach": true,
    "use_perceiver_resampler": true,
    "kv_cache": true,
    "enable_redaction": false,
    "reorder_and_upcast_attn": false,
    "scale_attn_by_inverse_layer_idx": false,
    "auto_map": {
      "AutoConfig": "AstraMindAI/xtts2-gpt--gpt_config.XTTSGPTConfig",
      "AutoModelForCausalLM": "AstraMindAI/xtts2-gpt--xtts2_gpt_modeling.XttsGPT",
      "AutoTokenizer": "AstraMindAI/xtts2-gpt--tokenizer.XTTSTokenizerFast"
    },
    "languages": [
      "en",
      "es",
      "fr",
      "de",
      "it",
      "pt",
      "pl",
      "tr",
      "ru",
      "nl",
      "cs",
      "ar",
      "zh-cn",
      "hu",
      "ko",
      "ja",
      "hi"
    ]
  },
  "gpt_code_stride_len": 1024,
  "cond_d_vector_in_each_upsampling_layer": true,
  "auto_map": {
    "AutoConfig": "AstraMindAI/xtts2--xtts2_config.XTTSConfig",
    "AutoModelForCausalLM": "AstraMindAI/xtts2--xtts2_modeling.Xtts",
    "AutoTokenizer": "AstraMindAI/xtts2--tokenizer.XTTSTokenizerFast"
  },
  "languages": [
    "en",
    "es",
    "fr",
    "de",
    "it",
    "pt",
    "pl",
    "tr",
    "ru",
    "nl",
    "cs",
    "ar",
    "zh-cn",
    "hu",
    "ko",
    "ja",
    "hi"
  ],
  "tokenizer_file": "",
  "transformers_version": "4.46.0"
}