Hugging Face's logo

hf-audio
/
xcodec2

Audio-to-Audio
Transformers
Safetensors
xcodec2
Model card Files
xet
Community
bezzam HF Staff commited on
Commit
2161d11
·
verified ·
1 Parent(s): d0d5a53

Upload model

Browse files
Files changed (2) hide show
  1. config.json +122 -0
  2. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Xcodec2Model"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "decoder_hidden_size": 1024,
8
+ "downsampling_ratios": [
9
+ 2,
10
+ 2,
11
+ 4,
12
+ 4,
13
+ 5
14
+ ],
15
+ "dtype": "float32",
16
+ "encoder_hidden_size": 1024,
17
+ "head_dim": 64,
18
+ "hidden_act": "silu",
19
+ "initializer_range": 0.02,
20
+ "max_position_embeddings": 4096,
21
+ "model_type": "xcodec2",
22
+ "num_attention_heads": 16,
23
+ "num_hidden_layers": 12,
24
+ "num_key_value_heads": 16,
25
+ "num_quantizers": 1,
26
+ "resnet_dropout": 0.1,
27
+ "rms_norm_eps": 1e-06,
28
+ "rope_theta": 10000.0,
29
+ "sampling_rate": 16000,
30
+ "semantic_model_config": {
31
+ "_name_or_path": "facebook/w2v-bert-2.0",
32
+ "activation_dropout": 0.0,
33
+ "adapter_act": "relu",
34
+ "adapter_kernel_size": 3,
35
+ "adapter_stride": 2,
36
+ "add_adapter": false,
37
+ "apply_spec_augment": false,
38
+ "architectures": [
39
+ "Wav2Vec2BertModel"
40
+ ],
41
+ "attention_dropout": 0.0,
42
+ "classifier_proj_size": 768,
43
+ "codevector_dim": 768,
44
+ "conformer_conv_dropout": 0.1,
45
+ "contrastive_logits_temperature": 0.1,
46
+ "conv_depthwise_kernel_size": 31,
47
+ "ctc_loss_reduction": "sum",
48
+ "ctc_zero_infinity": false,
49
+ "diversity_loss_weight": 0.1,
50
+ "dtype": "float32",
51
+ "feat_proj_dropout": 0.0,
52
+ "feat_quantizer_dropout": 0.0,
53
+ "feature_projection_input_dim": 160,
54
+ "final_dropout": 0.1,
55
+ "hidden_act": "swish",
56
+ "hidden_dropout": 0.0,
57
+ "hidden_size": 1024,
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 4096,
60
+ "layer_norm_eps": 1e-05,
61
+ "layerdrop": 0.1,
62
+ "left_max_position_embeddings": 64,
63
+ "mask_feature_length": 10,
64
+ "mask_feature_min_masks": 0,
65
+ "mask_feature_prob": 0.0,
66
+ "mask_time_length": 10,
67
+ "mask_time_min_masks": 2,
68
+ "mask_time_prob": 0.05,
69
+ "max_source_positions": 5000,
70
+ "model_type": "wav2vec2-bert",
71
+ "num_adapter_layers": 1,
72
+ "num_attention_heads": 16,
73
+ "num_codevector_groups": 2,
74
+ "num_codevectors_per_group": 320,
75
+ "num_hidden_layers": 24,
76
+ "num_negatives": 100,
77
+ "output_hidden_size": 1024,
78
+ "output_hidden_states": true,
79
+ "position_embeddings_type": "relative_key",
80
+ "proj_codevector_dim": 768,
81
+ "right_max_position_embeddings": 8,
82
+ "rotary_embedding_base": 10000,
83
+ "tdnn_dilation": [
84
+ 1,
85
+ 2,
86
+ 3,
87
+ 1,
88
+ 1
89
+ ],
90
+ "tdnn_dim": [
91
+ 512,
92
+ 512,
93
+ 512,
94
+ 512,
95
+ 1500
96
+ ],
97
+ "tdnn_kernel": [
98
+ 5,
99
+ 3,
100
+ 3,
101
+ 1,
102
+ 1
103
+ ],
104
+ "use_intermediate_ffn_before_adapter": false,
105
+ "use_weighted_layer_sum": false,
106
+ "vocab_size": null,
107
+ "xvector_output_dim": 512
108
+ },
109
+ "semantic_model_id": "facebook/w2v-bert-2.0",
110
+ "transformers_version": "4.56.0.dev0",
111
+ "vq_dim": 2048,
112
+ "vq_levels": [
113
+ 4,
114
+ 4,
115
+ 4,
116
+ 4,
117
+ 4,
118
+ 4,
119
+ 4,
120
+ 4
121
+ ]
122
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55f14a370b56875aca1f07220fed76d35927d7fd86d6106a7c2c9e0caede2029
3
+ size 3291056096