hf-transformers-bot's picture
Upload tiny models for Wav2Vec2ConformerForSequenceClassification
1394064
{
"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": [
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": false,
"eos_token_id": 2,
"feat_extract_activation": "gelu",
"feat_extract_dropout": 0.0,
"feat_extract_norm": "group",
"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": 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": 2,
"mask_time_min_masks": 2,
"mask_time_prob": 0.5,
"max_source_positions": 5000,
"model_type": "wav2vec2-conformer",
"num_adapter_layers": 1,
"num_attention_heads": 2,
"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": 100,
"output_hidden_size": 16,
"pad_token_id": 0,
"position_embeddings_type": "relative",
"proj_codevector_dim": 256,
"rotary_embedding_base": 10000,
"tdnn_dilation": [
1,
2
],
"tdnn_dim": [
32,
32
],
"tdnn_kernel": [
5,
3
],
"torch_dtype": "float32",
"transformers_version": "4.28.0.dev0",
"use_weighted_layer_sum": false,
"vocab_size": 32,
"xvector_output_dim": 32
}