bartelds's picture
Upload Wav2Vec2ForCTC
4aff3f9
raw
history blame
2.64 kB
{
"_name_or_path": "/nvme/restore/martijn/fine-tuning/gos/cp1_adp0_24m_no_test/wav2vec2-xls-r-300m-5e-5/checkpoint-13000",
"activation_dropout": 0.0,
"adapter_kernel_size": 3,
"adapter_stride": 2,
"add_adapter": false,
"apply_spec_augment": true,
"architectures": [
"Wav2Vec2ForCTC"
],
"attention_dropout": 0.1,
"bos_token_id": 1,
"bottleneck_adapter_act": "gelu",
"bottleneck_adapter_dim": 256,
"classifier_proj_size": 256,
"cnn_adapter_do_norm": true,
"cnn_adapter_in_conv_dim": 512,
"cnn_adapter_kernel": 1,
"cnn_adapter_out_conv_dim": 512,
"cnn_adapter_stride": 1,
"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": "mean",
"ctc_zero_infinity": true,
"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": 0.1,
"feat_quantizer_dropout": 0.0,
"final_dropout": 0.0,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout": 0.1,
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 4096,
"layer_norm_eps": 1e-05,
"layerdrop": 0.1,
"mask_feature_length": 10,
"mask_feature_min_masks": 0,
"mask_feature_prob": 0.004,
"mask_time_length": 10,
"mask_time_min_masks": 2,
"mask_time_prob": 0.075,
"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,
"pretrained_model_name_or_path": "/nvme/martijn/pre-training/checkpoints/gos-full-cpt/wav2vec2-xls-r-300m-gos-full-cpt-no-test-1e-5/checkpoint-100000/",
"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
],
"torch_dtype": "float32",
"transformers_version": "4.24.0",
"unfreeze_encoder": false,
"unfreeze_layernorm": false,
"use_bottleneck_adapter": false,
"use_cnn_adapter": false,
"use_weighted_layer_sum": false,
"vocab_size": 33,
"xvector_output_dim": 512
}