Keyword-Spotting / config.json
Amirhossein75's picture
add weights
e572ad5
{
"activation_dropout": 0.0,
"adapter_attn_dim": null,
"adapter_kernel_size": 3,
"adapter_stride": 2,
"add_adapter": false,
"apply_spec_augment": true,
"architectures": [
"Wav2Vec2ForSequenceClassification"
],
"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,
"id2label": {
"0": "backward",
"1": "bed",
"2": "bird",
"3": "cat",
"4": "dog",
"5": "down",
"6": "eight",
"7": "five",
"8": "follow",
"9": "forward",
"10": "four",
"11": "go",
"12": "happy",
"13": "house",
"14": "learn",
"15": "left",
"16": "marvin",
"17": "nine",
"18": "no",
"19": "off",
"20": "on",
"21": "one",
"22": "right",
"23": "seven",
"24": "sheila",
"25": "six",
"26": "stop",
"27": "three",
"28": "tree",
"29": "two",
"30": "up",
"31": "visual",
"32": "wow",
"33": "yes",
"34": "zero"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"backward": 0,
"bed": 1,
"bird": 2,
"cat": 3,
"dog": 4,
"down": 5,
"eight": 6,
"five": 7,
"follow": 8,
"forward": 9,
"four": 10,
"go": 11,
"happy": 12,
"house": 13,
"learn": 14,
"left": 15,
"marvin": 16,
"nine": 17,
"no": 18,
"off": 19,
"on": 20,
"one": 21,
"right": 22,
"seven": 23,
"sheila": 24,
"six": 25,
"stop": 26,
"three": 27,
"tree": 28,
"two": 29,
"up": 30,
"visual": 31,
"wow": 32,
"yes": 33,
"zero": 34
},
"layer_norm_eps": 1e-05,
"layerdrop": 0.0,
"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",
"model_type": "wav2vec2",
"no_mask_channel_overlap": false,
"no_mask_time_overlap": false,
"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,
"problem_type": "single_label_classification",
"proj_codevector_dim": 256,
"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": "4.55.3",
"use_weighted_layer_sum": false,
"vocab_size": 32,
"xvector_output_dim": 512
}