| New file |
| | |
| | | # network architecture |
| | | # encoder related |
| | | encoder: data2vec_encoder |
| | | encoder_conf: |
| | | extractor_mode: layer_norm |
| | | encoder_layerdrop: 0.05 |
| | | dropout_input: 0.0 |
| | | dropout_features: 0.0 |
| | | feature_grad_mult: 1.0 |
| | | encoder_embed_dim: 768 |
| | | |
| | | mask_prob: 0.65 |
| | | mask_length: 10 |
| | | |
| | | loss_beta: 0 |
| | | loss_scale: null |
| | | |
| | | instance_norm_target_layer: true |
| | | average_top_k_layers: 8 |
| | | |
| | | pos_conv_depth: 5 |
| | | conv_pos: 95 |
| | | |
| | | ema_decay: 0.999 |
| | | ema_end_decay: 0.9999 |
| | | ema_anneal_end_step: 30000 |
| | | ema_transformer_only: true |
| | | ema_layers_only: true |
| | | |
| | | require_same_masks: true |
| | | mask_dropout: 0 |
| | | |
| | | log_interval: 50 |
| | | normalize: None |
| | | |
| | | # minibatch related |
| | | batch_type: length |
| | | batch_bins: 64000 |
| | | num_workers: 16 |
| | | |
| | | # optimization related |
| | | accum_grad: 1 |
| | | grad_clip: 5 |
| | | patience: none |
| | | max_epoch: 600 |
| | | val_scheduler_criterion: |
| | | - valid |
| | | - acc |
| | | best_model_criterion: |
| | | - - valid |
| | | - loss |
| | | - min |
| | | keep_nbest_models: 50 |
| | | unused_parameters: true |
| | | |
| | | optim: fairseq_adam |
| | | optim_conf: |
| | | lr: 0.0005 |
| | | adam_betas: [0.9,0.98] |
| | | adam_eps: 1.0e-06 |
| | | weight_decay: 0.01 |
| | | |
| | | scheduler: tri_stage |
| | | scheduler_conf: |
| | | phase_ratio: [0.03,0.9,0.07] |
| | | |
| | | # for dataset |
| | | dataset_conf: |
| | | batch_mode: clipping |
| | | data_names: speech,none |
| | | data_types: kaldi_ark,none |
| | | shuffle: true |
| | | shuffle_conf: |
| | | shuffle_size: 12800 |
| | | sort_size: 12800 |
| | | batch_conf: |
| | | batch_type: token |
| | | batch_size: 64000 |
| | | num_workers: 8 |