data2vec-audio-base / config.json
patrickvonplaten's picture
Upload model & config
4b2131d
{
"activation_dropout": 0.1,
"adapter_kernel_size": 3,
"adapter_stride": 2,
"add_adapter": false,
"architectures": [
"Data2VecAudioModel"
],
"attention_dropout": 0.1,
"bos_token_id": 1,
"classifier_proj_size": 256,
"conv_bias": false,
"conv_dim": [
512,
512,
512,
512,
512,
512,
512
],
"conv_kernel": [
10,
3,
3,
3,
3,
2,
2
],
"conv_pos_kernel_size": 19,
"conv_stride": [
5,
2,
2,
2,
2,
2,
2
],
"ctc_loss_reduction": "sum",
"ctc_zero_infinity": false,
"eos_token_id": 2,
"feat_extract_activation": "gelu",
"feat_proj_dropout": 0.0,
"final_dropout": 0.1,
"hidden_act": "gelu",
"hidden_dropout": 0.1,
"hidden_size": 768,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_norm_eps": 1e-05,
"layerdrop": 0.1,
"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": 0.05,
"model_type": "data2vec-audio",
"num_adapter_layers": 3,
"num_attention_heads": 12,
"num_conv_pos_embedding_groups": 16,
"num_conv_pos_embeddings": 5,
"num_feat_extract_layers": 7,
"num_hidden_layers": 12,
"output_hidden_size": 768,
"pad_token_id": 0,
"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": "4.17.0.dev0",
"use_weighted_layer_sum": false,
"xvector_output_dim": 512
}