Hugging Face's logo

flax-community
/
wav2vec2-spanish

Automatic Speech Recognition
Transformers
PyTorch
JAX
Spanish
wav2vec2
pretraining
audio
Inference Endpoints
Model card Files Community
wav2vec2-spanish
File size: 2,051 Bytes 
69128c5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
    "activation_dropout": 0.0,
    "apply_spec_augment": true,
    "architectures": [
        "Wav2Vec2ForPreTraining"
    ],
    "attention_dropout": 0.1,
    "bos_token_id": 1,
    "codevector_dim": 256,
    "contrastive_logits_temperature": 0.1,
    "conv_bias": false,
    "conv_dim": [
        512,
        512,
        512,
        512,
        512,
        512,
        512
    ],
    "conv_kernel": [
        10,
        3,
        3,
        3,
        3,
        2,
        2
    ],
    "conv_stride": [
        5,
        2,
        2,
        2,
        2,
        2,
        2
    ],
    "ctc_loss_reduction": "sum",
    "ctc_zero_infinity": false,
    "diversity_loss_weight": 0.1,
    "do_stable_layer_norm": true,
    "eos_token_id": 2,
    "feat_extract_activation": "gelu",
    "feat_extract_norm": "layer",
    "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": 768,
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "layer_norm_eps": 1e-05,
    "layerdrop": 0.05,
    "mask_channel_length": 10,
    "mask_channel_min_space": 1,
    "mask_channel_other": 0.0,
    "mask_channel_prob": 0.0,
    "mask_channel_selection": "static",
    "mask_feature_length": 10,
    "mask_feature_prob": 0.0,
    "mask_time_length": 10,
    "mask_time_min_space": 1,
    "mask_time_other": 0.0,
    "mask_time_prob": 0.05,
    "mask_time_selection": "static",
    "model_type": "wav2vec2",
    "no_mask_channel_overlap": false,
    "no_mask_time_overlap": false,
    "num_attention_heads": 12,
    "num_codevector_groups": 2,
    "num_codevectors_per_group": 320,
    "num_conv_pos_embedding_groups": 16,
    "num_conv_pos_embeddings": 128,
    "num_feat_extract_layers": 7,
    "num_hidden_layers": 12,
    "num_negatives": 100,
    "pad_token_id": 0,
    "proj_codevector_dim": 256,
    "transformers_version": "4.9.0.dev0",
    "vocab_size": 32
}