my_awesome_mind_model / config.json
dbtmddn41's picture
first
4a7bcab
{
"_name_or_path": "facebook/wav2vec2-base",
"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": "_background_noise_",
"1": "audio",
"10": "go",
"11": "happy",
"12": "house",
"13": "left",
"14": "marvin",
"15": "nine",
"16": "no",
"17": "off",
"18": "on",
"19": "one",
"2": "bed",
"20": "right",
"21": "seven",
"22": "sheila",
"23": "six",
"24": "stop",
"25": "three",
"26": "tree",
"27": "two",
"28": "up",
"29": "wow",
"3": "bird",
"30": "yes",
"31": "zero",
"4": "cat",
"5": "dog",
"6": "down",
"7": "eight",
"8": "five",
"9": "four"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"_background_noise_": "0",
"audio": "1",
"bed": "2",
"bird": "3",
"cat": "4",
"dog": "5",
"down": "6",
"eight": "7",
"five": "8",
"four": "9",
"go": "10",
"happy": "11",
"house": "12",
"left": "13",
"marvin": "14",
"nine": "15",
"no": "16",
"off": "17",
"on": "18",
"one": "19",
"right": "20",
"seven": "21",
"sheila": "22",
"six": "23",
"stop": "24",
"three": "25",
"tree": "26",
"two": "27",
"up": "28",
"wow": "29",
"yes": "30",
"zero": "31"
},
"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,
"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": "4.35.2",
"use_weighted_layer_sum": false,
"vocab_size": 32,
"xvector_output_dim": 512
}