wavlm-base-plus-sd / config.json
{
"_name_or_path": "microsoft/wavlm-base-plus",
"activation_dropout": 0.0,
"adapter_kernel_size": 3,
"adapter_stride": 2,
"add_adapter": false,
"apply_spec_augment": true,
"architectures": [
"WavLMForAudioFrameClassification"
],
"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": [
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": 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,
"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_min_masks": 0,
"mask_feature_prob": 0.0,
"mask_time_length": 10,
"mask_time_min_masks": 2,
"mask_time_min_space": 1,
"mask_time_other": 0.0,
"mask_time_prob": 0.05,
"mask_time_selection": "static",
"max_bucket_distance": 800,
"model_type": "wavlm",
"no_mask_channel_overlap": false,
"no_mask_time_overlap": false,
"num_adapter_layers": 3,
"num_attention_heads": 12,
"num_buckets": 320,
"num_codevector_groups": 2,
"num_codevectors_per_group": 320,
"num_conv_pos_embedding_groups": 16,
"num_conv_pos_embeddings": 128,
"num_ctc_classes": 80,
"num_feat_extract_layers": 7,
"num_hidden_layers": 12,
"num_negatives": 100,
"output_hidden_size": 768,
"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
],
"tokenizer_class": "Wav2Vec2CTCTokenizer",
"torch_dtype": "float32",
"transformers_version": "4.15.0.dev0",
"use_weighted_layer_sum": true,
"vocab_size": 32,
"xvector_output_dim": 512
}