sew-small-100k-timit / config.json
{
"_name_or_path": "asapp/sew-small-100k",
"activation_dropout": 0.0,
"apply_spec_augment": true,
"architectures": [
"SEWForCTC"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"classifier_proj_size": 256,
"conv_bias": false,
"conv_dim": [
64,
128,
128,
128,
128,
256,
256,
256,
256,
512,
512,
512,
512
],
"conv_kernel": [
10,
3,
1,
3,
1,
3,
1,
3,
1,
2,
1,
2,
1
],
"conv_stride": [
5,
2,
1,
2,
1,
2,
1,
2,
1,
2,
1,
2,
1
],
"ctc_loss_reduction": "mean",
"ctc_zero_infinity": false,
"eos_token_id": 2,
"feat_extract_activation": "gelu",
"feat_extract_norm": "group",
"feat_proj_dropout": 0.0,
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
"final_dropout": 0.0,
"hidden_act": "gelu",
"hidden_dropout": 0.0,
"hidden_size": 768,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_norm_eps": 1e-05,
"layerdrop": 0.0,
"mask_feature_length": 10,
"mask_feature_prob": 0.0,
"mask_time_length": 10,
"mask_time_prob": 0.05,
"model_type": "sew",
"num_attention_heads": 12,
"num_conv_pos_embedding_groups": 16,
"num_conv_pos_embeddings": 31,
"num_feat_extract_layers": 13,
"num_hidden_layers": 12,
"pad_token_id": 28,
"squeeze_factor": 2,
"tokenizer_class": "Wav2Vec2CTCTokenizer",
"torch_dtype": "float32",
"transformers_version": "4.12.0.dev0",
"use_weighted_layer_sum": false,
"vocab_size": 31
}