zh_w2v2_tiny_fc_10ms / config.json
charsiu's picture
Upload config.json
7162a10
{
"_name_or_path": "/home/lingjzhu/TED/models/wav2vec2-multicn-pretraining/checkpoint-25000",
"activation_dropout": 0.1,
"apply_spec_augment": true,
"architectures": [
"Wav2Vec2ForFrameClassification"
],
"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,
1
],
"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": 0.1,
"hidden_act": "gelu",
"hidden_dropout": 0.1,
"hidden_size": 384,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_norm_eps": 1e-05,
"layerdrop": 0.1,
"mask_feature_length": 10,
"mask_feature_prob": 0.0,
"mask_time_length": 10,
"mask_time_prob": 0.05,
"model_type": "wav2vec2",
"num_attention_heads": 6,
"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": 6,
"num_negatives": 20,
"pad_token_id": 0,
"proj_codevector_dim": 256,
"torch_dtype": "float32",
"transformers_version": "4.12.5",
"use_weighted_layer_sum": false,
"vocab_size": 210
}