speech-test's picture
Upload model
99317c6
{
"_name_or_path": "facebook/wav2vec2-large-lv60",
"activation_dropout": 0.1,
"apply_spec_augment": true,
"architectures": [
"Wav2Vec2ForSequenceClassification"
],
"attention_dropout": 0.1,
"bos_token_id": 1,
"classifier_proj_size": 256,
"codevector_dim": 768,
"contrastive_logits_temperature": 0.1,
"conv_bias": true,
"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": 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": 1024,
"id2label": {
"0": "change language",
"1": "activate",
"2": "deactivate",
"3": "increase",
"4": "decrease",
"5": "bring",
"6": "none_object",
"7": "music",
"8": "lights",
"9": "volume",
"10": "heat",
"11": "lamp",
"12": "newspaper",
"13": "juice",
"14": "socks",
"15": "Chinese",
"16": "Korean",
"17": "English",
"18": "German",
"19": "shoes",
"20": "none_location",
"21": "kitchen",
"22": "bedroom",
"23": "washroom"
},
"initializer_range": 0.02,
"intermediate_size": 4096,
"label2id": {
"Chinese": 15,
"English": 17,
"German": 18,
"Korean": 16,
"activate": 1,
"bedroom": 22,
"bring": 5,
"change language": 0,
"deactivate": 2,
"decrease": 4,
"heat": 10,
"increase": 3,
"juice": 13,
"kitchen": 21,
"lamp": 11,
"lights": 8,
"music": 7,
"newspaper": 12,
"none_location": 20,
"none_object": 6,
"shoes": 19,
"socks": 14,
"volume": 9,
"washroom": 23
},
"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": "wav2vec2",
"num_attention_heads": 16,
"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": 24,
"num_negatives": 100,
"pad_token_id": 0,
"proj_codevector_dim": 768,
"torch_dtype": "float32",
"transformers_version": "4.11.0.dev0",
"use_weighted_layer_sum": true,
"vocab_size": 32
}