Hugging Face's logo

Ambiq
/
compressionkit-e2a2-audio-v0.3

LiteRT
Model card Files
xet
 Community
compressionkit-e2a2-audio-v0.3
File size: 2,280 Bytes
4e60ba0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "codec": "E2A2",
  "format": "e2a2_hub1",
  "source_checkpoint": "e2a2a_g7.pth",
  "modality": "audio",
  "dim": 1,
  "input_channels": 2,
  "ps": [
    256,
    256,
    128,
    64,
    32,
    16,
    8
  ],
  "group_sizes": [
    4,
    5,
    6,
    6,
    12,
    9,
    9
  ],
  "cumulative_channels": [
    4,
    9,
    15,
    21,
    33,
    42,
    51
  ],
  "n_groups": 7,
  "affine": true,
  "linear_input": false,
  "decoder_configs": [
    {
      "decoder_ps": 128,
      "decoder_dim": 1024,
      "decoder_kernel_size": 3,
      "decoder_depth": 12,
      "decoder_mlp_ratio": 4,
      "decoder_layerscale": true,
      "decoder_layerscale_init": 1e-06
    },
    {
      "decoder_ps": 128,
      "decoder_dim": 1024,
      "decoder_kernel_size": 3,
      "decoder_depth": 12,
      "decoder_mlp_ratio": 4,
      "decoder_layerscale": true,
      "decoder_layerscale_init": 1e-06
    },
    {
      "decoder_ps": 128,
      "decoder_dim": 1024,
      "decoder_kernel_size": 3,
      "decoder_depth": 24,
      "decoder_mlp_ratio": 4,
      "decoder_layerscale": true,
      "decoder_layerscale_init": 1e-06
    },
    {
      "decoder_ps": 128,
      "decoder_dim": 1024,
      "decoder_kernel_size": 3,
      "decoder_depth": 24,
      "decoder_mlp_ratio": 4,
      "decoder_layerscale": true,
      "decoder_layerscale_init": 1e-06
    },
    {
      "decoder_ps": 128,
      "decoder_dim": 1024,
      "decoder_kernel_size": 3,
      "decoder_depth": 24,
      "decoder_mlp_ratio": 4,
      "decoder_layerscale": true,
      "decoder_layerscale_init": 1e-06
    },
    {
      "decoder_ps": 128,
      "decoder_dim": 1024,
      "decoder_kernel_size": 3,
      "decoder_depth": 24,
      "decoder_mlp_ratio": 4,
      "decoder_layerscale": true,
      "decoder_layerscale_init": 1e-06
    },
    {
      "decoder_ps": 128,
      "decoder_dim": 1024,
      "decoder_kernel_size": 3,
      "decoder_depth": 24,
      "decoder_mlp_ratio": 4,
      "decoder_layerscale": true,
      "decoder_layerscale_init": 1e-06
    }
  ],
  "macroregion": 16384,
  "stream_mode": "all_detail",
  "compander": "softsign",
  "compander_bits": 6,
  "alphabet": [
    -31,
    31
  ],
  "input_range": [
    -1,
    1
  ],
  "sample_rate": 44100,
  "val_normalize": "peak"
}