wav2vec2-ctc-chime4 / config.json
esc-bencher's picture
Add training scripts and weights
d644c71
{
"activation_dropout": 0.2,
"adapter_kernel_size": 3,
"adapter_stride": 2,
"add_adapter": false,
"apply_spec_augment": true,
"architectures": [
"Wav2Vec2ForCTC"
],
"attention_dropout": 0.1,
"bos_token_id": 1,
"classifier_proj_size": 256,
"codevector_dim": 768,
"contrastive_logits_temperature": 0.1,
"conv_bias": true,
"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": true,
"eos_token_id": 2,
"feat_extract_activation": "gelu",
"feat_extract_dropout": 0.0,
"feat_extract_norm": "layer",
"feat_proj_dropout": 0.2,
"feat_quantizer_dropout": 0.0,
"final_dropout": 0.0,
"fuse_matmuls": false,
"gradient_checkpointing": true,
"hidden_act": "gelu",
"hidden_dropout": 0.2,
"hidden_dropout_prob": 0.1,
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 4096,
"layer_norm_eps": 1e-05,
"layerdrop": 0.0,
"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_prob": 0.1,
"model_type": "wav2vec2",
"num_adapter_layers": 3,
"num_attention_heads": 16,
"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": 24,
"num_negatives": 100,
"output_hidden_size": 1024,
"pad_token_id": 0,
"proj_codevector_dim": 768,
"tdnn_dilation": [
1,
2,
3,
1,
1
],
"tdnn_dim": [
512,
512,
512,
512,
1500
],
"tdnn_kernel": [
5,
3,
3,
1,
1
],
"transformers_version": "4.21.0.dev0",
"use_scan": true,
"use_weighted_layer_sum": false,
"vocab_size": 63,
"xvector_output_dim": 512
}