Hugging Face's logo

anton-l
/
wav2vec2-random-tiny-classifier

Audio Classification
Transformers
PyTorch
wav2vec2
Inference Endpoints
Model card Files Community
1
wav2vec2-random-tiny-classifier
File size: 2,049 Bytes 
2838dc5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "_name_or_path": "anton-l/wav2vec2-random-tiny-classifier",
  "activation_dropout": 0.0,
  "apply_spec_augment": true,
  "architectures": [
    "Wav2Vec2ForSequenceClassification"
  ],
  "attention_dropout": 0.1,
  "bos_token_id": 1,
  "classifier_proj_size": 16,
  "codevector_dim": 256,
  "contrastive_logits_temperature": 0.1,
  "conv_bias": false,
  "conv_dim": [
    32
  ],
  "conv_kernel": [
    2
  ],
  "conv_stride": [
    320
  ],
  "ctc_loss_reduction": "sum",
  "ctc_zero_infinity": false,
  "diversity_loss_weight": 0.1,
  "do_stable_layer_norm": false,
  "eos_token_id": 2,
  "feat_extract_activation": "gelu",
  "feat_extract_norm": "group",
  "feat_proj_dropout": 0.1,
  "feat_quantizer_dropout": 0.0,
  "final_dropout": 0.0,
  "freeze_feat_extract_train": true,
  "gradient_checkpointing": true,
  "hidden_act": "gelu",
  "hidden_dropout": 0.1,
  "hidden_size": 32,
  "id2label": {
    "0": "yes",
    "1": "no",
    "2": "up",
    "3": "down",
    "4": "left",
    "5": "right",
    "6": "on",
    "7": "off",
    "8": "stop",
    "9": "go",
    "10": "_unknown_",
    "11": "_silence_"
  },
  "initializer_range": 0.02,
  "intermediate_size": 32,
  "label2id": {
    "_silence_": 11,
    "_unknown_": 10,
    "down": 3,
    "go": 9,
    "left": 4,
    "no": 1,
    "off": 7,
    "on": 6,
    "right": 5,
    "stop": 8,
    "up": 2,
    "yes": 0
  },
  "layer_norm_eps": 1e-05,
  "layerdrop": 0.05,
  "mask_feature_length": 10,
  "mask_feature_prob": 0.0,
  "mask_time_length": 10,
  "mask_time_prob": 0.05,
  "model_type": "wav2vec2",
  "no_mask_channel_overlap": false,
  "no_mask_time_overlap": false,
  "num_attention_heads": 2,
  "num_codevector_groups": 2,
  "num_codevectors_per_group": 320,
  "num_conv_pos_embedding_groups": 2,
  "num_conv_pos_embeddings": 8,
  "num_feat_extract_layers": 1,
  "num_hidden_layers": 2,
  "num_negatives": 100,
  "pad_token_id": 0,
  "proj_codevector_dim": 256,
  "torch_dtype": "float32",
  "transformers_version": "4.10.0.dev0",
  "use_weighted_layer_sum": true,
  "vocab_size": 32
}