{ | |
"architectures": [ | |
"Wav2Vec2ForCTC" | |
], | |
"attention_probs_dropout_prob": 0.1, | |
"bos_token_id": 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 | |
], | |
"do_stable_layer_norm": false, | |
"eos_token_id": 2, | |
"feat_extract_activation": "gelu", | |
"feat_extract_dropout": 0.0, | |
"feat_extract_norm": "group", | |
"hidden_act": "gelu", | |
"hidden_dropout_prob": 0.1, | |
"hidden_size": 768, | |
"initializer_range": 0.02, | |
"intermediate_size": 3072, | |
"layer_norm_eps": 1e-05, | |
"model_type": "wav2vec2", | |
"num_attention_heads": 12, | |
"num_conv_pos_embedding_groups": 16, | |
"num_conv_pos_embeddings": 128, | |
"num_feat_extract_layers": 7, | |
"num_hidden_layers": 12, | |
"pad_token_id": 0, | |
"transformers_version": "4.3.2", | |
"vocab_size": 32 | |
} | |