| egs/aishell/branchformer/conf/train_asr_branchformer_bs10000.yaml | ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史 | |
| egs/aishell/branchformer/conf/train_asr_branchformer_bs16000_gc2.yaml | ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史 | |
| egs/aishell/branchformer/run.sh | ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史 |
egs/aishell/branchformer/conf/train_asr_branchformer_bs10000.yaml
New file @@ -0,0 +1,104 @@ # network architecture # encoder related encoder: branchformer encoder_conf: output_size: 256 use_attn: true attention_heads: 4 attention_layer_type: rel_selfattn pos_enc_layer_type: rel_pos rel_pos_type: latest use_cgmlp: true cgmlp_linear_units: 2048 cgmlp_conv_kernel: 31 use_linear_after_conv: false gate_activation: identity merge_method: concat cgmlp_weight: 0.5 # used only if merge_method is "fixed_ave" attn_branch_drop_rate: 0.0 # used only if merge_method is "learned_ave" num_blocks: 24 dropout_rate: 0.1 positional_dropout_rate: 0.1 attention_dropout_rate: 0.1 input_layer: conv2d stochastic_depth_rate: 0.0 # decoder related decoder: transformer decoder_conf: attention_heads: 4 linear_units: 2048 num_blocks: 6 dropout_rate: 0.1 positional_dropout_rate: 0.1 self_attention_dropout_rate: 0. src_attention_dropout_rate: 0. # frontend related frontend: wav_frontend frontend_conf: fs: 16000 window: hamming n_mels: 80 frame_length: 25 frame_shift: 10 lfr_m: 1 lfr_n: 1 # hybrid CTC/attention model_conf: ctc_weight: 0.3 lsm_weight: 0.1 # label smoothing option length_normalized_loss: false # optimization related accum_grad: 1 grad_clip: 5 max_epoch: 180 val_scheduler_criterion: - valid - acc best_model_criterion: - - valid - acc - max keep_nbest_models: 10 optim: adam optim_conf: lr: 0.001 weight_decay: 0.000001 scheduler: warmuplr scheduler_conf: warmup_steps: 35000 specaug: specaug specaug_conf: apply_time_warp: true time_warp_window: 5 time_warp_mode: bicubic apply_freq_mask: true freq_mask_width_range: - 0 - 27 num_freq_mask: 2 apply_time_mask: true time_mask_width_ratio_range: - 0. - 0.05 num_time_mask: 10 dataset_conf: data_names: speech,text data_types: sound,text shuffle: True shuffle_conf: shuffle_size: 2048 sort_size: 500 batch_conf: batch_type: token batch_size: 10000 num_workers: 8 log_interval: 50 normalize: None egs/aishell/branchformer/conf/train_asr_branchformer_bs16000_gc2.yaml
New file @@ -0,0 +1,104 @@ # network architecture # encoder related encoder: branchformer encoder_conf: output_size: 256 use_attn: true attention_heads: 4 attention_layer_type: rel_selfattn pos_enc_layer_type: rel_pos rel_pos_type: latest use_cgmlp: true cgmlp_linear_units: 2048 cgmlp_conv_kernel: 31 use_linear_after_conv: false gate_activation: identity merge_method: concat cgmlp_weight: 0.5 # used only if merge_method is "fixed_ave" attn_branch_drop_rate: 0.0 # used only if merge_method is "learned_ave" num_blocks: 24 dropout_rate: 0.1 positional_dropout_rate: 0.1 attention_dropout_rate: 0.1 input_layer: conv2d stochastic_depth_rate: 0.0 # decoder related decoder: transformer decoder_conf: attention_heads: 4 linear_units: 2048 num_blocks: 6 dropout_rate: 0.1 positional_dropout_rate: 0.1 self_attention_dropout_rate: 0. src_attention_dropout_rate: 0. # frontend related frontend: wav_frontend frontend_conf: fs: 16000 window: hamming n_mels: 80 frame_length: 25 frame_shift: 10 lfr_m: 1 lfr_n: 1 # hybrid CTC/attention model_conf: ctc_weight: 0.3 lsm_weight: 0.1 # label smoothing option length_normalized_loss: false # optimization related accum_grad: 2 grad_clip: 5 max_epoch: 180 val_scheduler_criterion: - valid - acc best_model_criterion: - - valid - acc - max keep_nbest_models: 10 optim: adam optim_conf: lr: 0.001 weight_decay: 0.000001 scheduler: warmuplr scheduler_conf: warmup_steps: 35000 specaug: specaug specaug_conf: apply_time_warp: true time_warp_window: 5 time_warp_mode: bicubic apply_freq_mask: true freq_mask_width_range: - 0 - 27 num_freq_mask: 2 apply_time_mask: true time_mask_width_ratio_range: - 0. - 0.05 num_time_mask: 10 dataset_conf: data_names: speech,text data_types: sound,text shuffle: True shuffle_conf: shuffle_size: 2048 sort_size: 500 batch_conf: batch_type: token batch_size: 16000 num_workers: 8 log_interval: 50 normalize: None egs/aishell/branchformer/run.sh
@@ -47,7 +47,9 @@ test_sets="dev test" #asr_config=conf/train_asr_branchformer.yaml asr_config=conf/train_asr_branchformer_bs16000.yaml #asr_config=conf/train_asr_branchformer_bs16000.yaml asr_config=conf/train_asr_branchformer_bs16000_gc2.yaml #asr_config=conf/train_asr_branchformer_bs10000.yaml model_dir="baseline_$(basename "${asr_config}" .yaml)_${lang}_${token_type}_${tag}" inference_config=conf/decode_asr_transformer.yaml
