File size: 1,907 Bytes
f91ea52 4a77977 f91ea52 4a77977 f91ea52 5a16a0c f91ea52 5a16a0c f91ea52 5a16a0c f91ea52 5a16a0c f91ea52 5a16a0c f91ea52 5a16a0c f91ea52 5a16a0c f91ea52 5a16a0c f91ea52 4a77977 f91ea52 4a77977 f91ea52 5a16a0c f91ea52 5a16a0c f91ea52 4a77977 f91ea52 4a77977 f91ea52 4a77977 f91ea52 |
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 |
{
"_name_or_path": "./",
"activation_dropout": 0.1,
"apply_spec_augment": true,
"architectures": [
"UniSpeechSatForSequenceClassification"
],
"attention_dropout": 0.1,
"bos_token_id": 1,
"classifier_proj_size": 256,
"codevector_dim": 256,
"contrastive_logits_temperature": 0.1,
"conv_bias": false,
"conv_dim": [
32,
32,
32
],
"conv_kernel": [
8,
8,
8
],
"conv_stride": [
4,
4,
4
],
"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_dropout": 0.0,
"feat_extract_norm": "layer",
"feat_proj_dropout": 0.1,
"feat_quantizer_dropout": 0.0,
"final_dropout": 0.1,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout": 0.1,
"hidden_dropout_prob": 0.1,
"hidden_size": 16,
"initializer_range": 0.02,
"intermediate_size": 20,
"layer_norm_eps": 1e-05,
"layerdrop": 0.1,
"mask_feature_length": 10,
"mask_feature_min_masks": 0,
"mask_feature_prob": 0.0,
"mask_time_length": 10,
"mask_time_min_masks": 2,
"mask_time_prob": 0.05,
"model_type": "unispeech-sat",
"num_attention_heads": 2,
"num_clusters": 504,
"num_codevector_groups": 2,
"num_codevectors_per_group": 320,
"num_conv_pos_embedding_groups": 2,
"num_conv_pos_embeddings": 16,
"num_feat_extract_layers": 3,
"num_hidden_layers": 4,
"num_negatives": 10,
"pad_token_id": 0,
"proj_codevector_dim": 256,
"replace_prob": 0.5,
"tdnn_dilation": [
1,
2,
3,
1,
1
],
"tdnn_dim": [
512,
512,
512,
512,
1500
],
"tdnn_kernel": [
5,
3,
3,
1,
1
],
"torch_dtype": "float32",
"transformers_version": "4.16.0.dev0",
"use_weighted_layer_sum": false,
"vocab_size": 32,
"xvector_output_dim": 512
}
|