config.json
2.1 KB · 112 lines · json Raw
1 {
2 "_name_or_path": "facebook/wav2vec2-xls-r-300m",
3 "activation_dropout": 0.0,
4 "adapter_attn_dim": null,
5 "adapter_kernel_size": 3,
6 "adapter_stride": 2,
7 "add_adapter": false,
8 "apply_spec_augment": true,
9 "architectures": [
10 "Wav2Vec2ForSequenceClassification"
11 ],
12 "attention_dropout": 0.1,
13 "bos_token_id": 1,
14 "classifier_proj_size": 256,
15 "codevector_dim": 768,
16 "contrastive_logits_temperature": 0.1,
17 "conv_bias": true,
18 "conv_dim": [
19 512,
20 512,
21 512,
22 512,
23 512,
24 512,
25 512
26 ],
27 "conv_kernel": [
28 10,
29 3,
30 3,
31 3,
32 3,
33 2,
34 2
35 ],
36 "conv_stride": [
37 5,
38 2,
39 2,
40 2,
41 2,
42 2,
43 2
44 ],
45 "id2label": {"0": "human", "1": "voicemail"},
46 "label2id": {"human": 0, "voicemail": 1},
47 "ctc_loss_reduction": "sum",
48 "ctc_zero_infinity": false,
49 "diversity_loss_weight": 0.1,
50 "do_stable_layer_norm": true,
51 "eos_token_id": 2,
52 "feat_extract_activation": "gelu",
53 "feat_extract_dropout": 0.0,
54 "feat_extract_norm": "layer",
55 "feat_proj_dropout": 0.1,
56 "feat_quantizer_dropout": 0.0,
57 "final_dropout": 0.0,
58 "gradient_checkpointing": false,
59 "hidden_act": "gelu",
60 "hidden_dropout": 0.1,
61 "hidden_size": 1024,
62 "initializer_range": 0.02,
63 "intermediate_size": 4096,
64 "layer_norm_eps": 1e-05,
65 "layerdrop": 0.1,
66 "mask_feature_length": 10,
67 "mask_feature_min_masks": 0,
68 "mask_feature_prob": 0.0,
69 "mask_time_length": 10,
70 "mask_time_min_masks": 2,
71 "mask_time_prob": 0.075,
72 "model_type": "wav2vec2",
73 "num_adapter_layers": 3,
74 "num_attention_heads": 16,
75 "num_codevector_groups": 2,
76 "num_codevectors_per_group": 320,
77 "num_conv_pos_embedding_groups": 16,
78 "num_conv_pos_embeddings": 128,
79 "num_feat_extract_layers": 7,
80 "num_hidden_layers": 24,
81 "num_negatives": 100,
82 "output_hidden_size": 1024,
83 "pad_token_id": 0,
84 "proj_codevector_dim": 768,
85 "tdnn_dilation": [
86 1,
87 2,
88 3,
89 1,
90 1
91 ],
92 "tdnn_dim": [
93 512,
94 512,
95 512,
96 512,
97 1500
98 ],
99 "tdnn_kernel": [
100 5,
101 3,
102 3,
103 1,
104 1
105 ],
106 "torch_dtype": "float32",
107 "transformers_version": "4.48.2",
108 "use_weighted_layer_sum": false,
109 "vocab_size": 32,
110 "xvector_output_dim": 512
111 }
112