w2v2c_ko_emotion / config.json
JUNGWJ's picture
Training in progress, epoch 0
9fa0696
{
"_name_or_path": "42MARU/ko-spelling-wav2vec2-conformer-del-1s",
"activation_dropout": 0.1,
"adapter_kernel_size": 3,
"adapter_stride": 2,
"add_adapter": false,
"apply_spec_augment": true,
"architectures": [
"Wav2Vec2ConformerForSequenceClassification"
],
"attention_dropout": 0.1,
"bos_token_id": 1,
"classifier_proj_size": 256,
"codevector_dim": 256,
"conformer_conv_dropout": 0.1,
"contrastive_logits_temperature": 0.1,
"conv_bias": false,
"conv_depthwise_kernel_size": 31,
"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": "mean",
"ctc_zero_infinity": true,
"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": 0.0,
"feat_quantizer_dropout": 0.0,
"final_dropout": 0.1,
"hidden_act": "gelu",
"hidden_dropout": 0.1,
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "Happy",
"1": "Sad",
"2": "Angry",
"3": "Anxious"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"Angry": "2",
"Anxious": "3",
"Happy": "0",
"Sad": "1"
},
"layer_norm_eps": 1e-05,
"layerdrop": 0.0,
"mask_feature_length": 64,
"mask_feature_min_masks": 0,
"mask_feature_prob": 0.05,
"mask_time_length": 10,
"mask_time_min_masks": 2,
"mask_time_prob": 0.05,
"max_source_positions": 5000,
"model_type": "wav2vec2-conformer",
"num_adapter_layers": 3,
"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,
"output_hidden_size": 768,
"pad_token_id": 0,
"position_embeddings_type": "relative",
"proj_codevector_dim": 256,
"rotary_embedding_base": 10000,
"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": "4.24.0",
"use_weighted_layer_sum": false,
"vocab_size": 111,
"xvector_output_dim": 512
}