hubert-base-superb-ks / config.json
speech-test's picture
Upload model
20f885c
{
"_name_or_path": "facebook/hubert-base-ls960",
"activation_dropout": 0.1,
"apply_spec_augment": true,
"architectures": [
"HubertForSequenceClassification"
],
"attention_dropout": 0.1,
"bos_token_id": 1,
"classifier_proj_size": 256,
"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,
"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": 0.1,
"final_dropout": 0.1,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout": 0.1,
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "yes",
"1": "no",
"2": "up",
"3": "down",
"4": "left",
"5": "right",
"6": "on",
"7": "off",
"8": "stop",
"9": "go",
"10": "_unknown_",
"11": "_silence_"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"_silence_": 11,
"_unknown_": 10,
"down": 3,
"go": 9,
"left": 4,
"no": 1,
"off": 7,
"on": 6,
"right": 5,
"stop": 8,
"up": 2,
"yes": 0
},
"layer_norm_eps": 1e-05,
"layerdrop": 0.1,
"mask_feature_length": 10,
"mask_feature_prob": 0.0,
"mask_time_length": 10,
"mask_time_prob": 0.05,
"model_type": "hubert",
"num_attention_heads": 12,
"num_conv_pos_embedding_groups": 16,
"num_conv_pos_embeddings": 128,
"num_feat_extract_layers": 7,
"num_hidden_layers": 12,
"pad_token_id": 0,
"problem_type": "single_label_classification",
"torch_dtype": "float32",
"transformers_version": "4.10.0.dev0",
"use_weighted_layer_sum": true,
"vocab_size": 32
}