sb-noise2vec / config.json
akera's picture
Upload 9 files
b64e27e verified
{
"_name_or_path": "facebook/wav2vec2-base",
"activation_dropout": 0.0,
"adapter_kernel_size": 3,
"adapter_stride": 2,
"add_adapter": false,
"apply_spec_augment": true,
"architectures": [
"Wav2Vec2ForSpeechClassification"
],
"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,
"finetuning_task": "wav2vec2_clf",
"freeze_feat_extract_train": true,
"hidden_act": "gelu",
"hidden_dropout": 0.1,
"hidden_size": 768,
"id2label": {
"0": "animal",
"1": "bar-restaurant-nightclub",
"2": "boda-boda-motocyle",
"3": "car-alarm",
"4": "car-or-truck",
"5": "community-radio",
"6": "construction-site",
"7": "crowd-noise",
"8": "fabrication-workshop",
"9": "generator",
"10": "hawker-vendor",
"11": "herbalists",
"12": "mobile-music",
"13": "motorvehicle-horn",
"14": "motorvehicle-siren",
"15": "other",
"16": "regilious-venue",
"17": "school",
"18": "street-preacher"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"animal": 0,
"bar-restaurant-nightclub": 1,
"boda-boda-motocyle": 2,
"car-alarm": 3,
"car-or-truck": 4,
"community-radio": 5,
"construction-site": 6,
"crowd-noise": 7,
"fabrication-workshop": 8,
"generator": 9,
"hawker-vendor": 10,
"herbalists": 11,
"mobile-music": 12,
"motorvehicle-horn": 13,
"motorvehicle-siren": 14,
"other": 15,
"regilious-venue": 16,
"school": 17,
"street-preacher": 18
},
"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,
"pooling_mode": "mean",
"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": "4.16.2",
"use_weighted_layer_sum": false,
"vocab_size": 32,
"xvector_output_dim": 512
}