Hugging Face's logo

JusperLee
/
Dolphin

Audio-to-Audio
PyTorch
Safetensors
English
dolphin
audio-visual
speech-separation
cocktail-party
multimodal
lip-reading
audio-processing
custom_code
Model card Files
xet
Community
1
Dolphin
File size: 2,805 Bytes 
0f50241
5c69d39
 
 
 
 
 
 
 
 
 
 
44a284d
 
 
 
 
 
5c69d39
 
 
 
 
 
44a284d
 
 
5c69d39
 
 
 
44a284d
 
 
 
5c69d39
 
 
44a284d
 
5c69d39
 
 
 
 
 
 
 
44a284d
08cf5a5
5c69d39
 
08cf5a5
44a284d
 
5c69d39
 
08cf5a5
44a284d
 
 
5c69d39
 
 
 
 
 
44a284d
 
5c69d39
 
44a284d
 
 
5c69d39
 
 
 
 
 
 
44a284d
08cf5a5
0f50241
5c69d39
 
 
 
 
 
 
 
 
 
 
44a284d
 
 
 
 
 
 
 
 
 
 
 
5c69d39
 
 
44a284d
5c69d39
 
 
 
 
44a284d
 
 
 
 
5c69d39
44a284d
5c69d39
 
 
 
 
 
 
 
 
 
 
 
0f50241
 
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
 
{
  "model_type": "dolphin",
  "task": "audio_visual_speech_separation",
  "framework": "pytorch",
  "license": "apache-2.0",
  "tags": [
    "audio",
    "speech-separation",
    "audio-visual",
    "pytorch",
    "dolphin"
  ],
  "architectures": [
    "Dolphin"
  ],
  "auto_map": {
    "AutoModel": "dolphin.Dolphin"
  },
  "num_stages": 4,
  "sample_rate": 16000,
  "vpre_channels": 3872,
  "vmid_channels": 512,
  "vin_channels": 64,
  "vout_channels": 64,
  "module_audio_enc": {
    "in_channels": 1,
    "out_channels": 256,
    "kernel_size": 16,
    "stride": 4,
    "groups": 1,
    "bias": false
  },
  "module_feature_projector": {
    "num_channels": 256,
    "in_channels": 256,
    "out_channels": 128,
    "kernel_size": 1,
    "bias": false
  },
  "module_separator": {
    "num_stages": 4,
    "relative_positional_encoding": {
      "in_channels": 128,
      "num_heads": 8,
      "maxlen": 2000,
      "embed_v": false
    },
    "enc_stage": {
      "global_blocks": {
        "in_channels": 128,
        "num_mha_heads": 8,
        "dropout_rate": 0.05
      },
      "local_blocks": {
        "in_channels": 128,
        "kernel_size": 65,
        "dropout_rate": 0.05
      },
      "down_conv_layer": {
        "in_channels": 128,
        "samp_kernel_size": 5
      }
    },
    "simple_fusion": {
      "out_channels": 128
    },
    "dec_stage": {
      "global_blocks": {
        "in_channels": 128,
        "num_mha_heads": 8,
        "dropout_rate": 0.05
      },
      "local_blocks": {
        "in_channels": 128,
        "kernel_size": 65,
        "dropout_rate": 0.05
      },
      "spk_attention": {
        "in_channels": 128,
        "num_mha_heads": 8,
        "dropout_rate": 0.05
      }
    }
  },
  "module_output_layer": {
    "in_channels": 256,
    "out_channels": 128
  },
  "module_audio_dec": {
    "in_channels": 256,
    "out_channels": 1,
    "kernel_size": 16,
    "stride": 4,
    "bias": false
  },
  "video_encoder_params": {
    "layers": [
      "residual",
      "compress_space",
      "consecutive_residual",
      "compress_space",
      "consecutive_residual",
      "linear_attend_space",
      "compress_space",
      "consecutive_residual",
      "attend_space"
    ],
    "image_size": 88,
    "in_channel": 1,
    "init_channel": 4,
    "max_dim": 32,
    "input_conv_kernel_size": [
      7,
      7,
      7
    ],
    "output_conv_kernel_size": [
      3,
      3,
      3
    ],
    "residual_conv_kernel_size": 3,
    "pad_mode": "constant",
    "attn_dim_head": 32,
    "attn_heads": 8,
    "attn_dropout": 0.0,
    "flash_attn": true,
    "linear_attn_dim_head": 8,
    "linear_attn_heads": 16,
    "num_quantizers": 1,
    "codebook_size": 256,
    "codebook_dim": 64,
    "commitment_cost": 1.0,
    "distill_cost": 1.0
  }
}