From da1544fcbc572a22eaeee6179614a26eb2bc39d5 Mon Sep 17 00:00:00 2001
From: 嘉渊 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期六, 08 七月 2023 02:44:42 +0800
Subject: [PATCH] update
---
egs/aishell/branchformer/conf/train_asr_branchformer_bs16000_gc2.yaml | 104 ++++++++++++++++++++++++++
egs/aishell/branchformer/run.sh | 4
egs/aishell/branchformer/conf/train_asr_branchformer_bs10000.yaml | 104 ++++++++++++++++++++++++++
3 files changed, 211 insertions(+), 1 deletions(-)
diff --git a/egs/aishell/branchformer/conf/train_asr_branchformer_bs10000.yaml b/egs/aishell/branchformer/conf/train_asr_branchformer_bs10000.yaml
new file mode 100644
index 0000000..f35c897
--- /dev/null
+++ b/egs/aishell/branchformer/conf/train_asr_branchformer_bs10000.yaml
@@ -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
\ No newline at end of file
diff --git a/egs/aishell/branchformer/conf/train_asr_branchformer_bs16000_gc2.yaml b/egs/aishell/branchformer/conf/train_asr_branchformer_bs16000_gc2.yaml
new file mode 100644
index 0000000..bd5d934
--- /dev/null
+++ b/egs/aishell/branchformer/conf/train_asr_branchformer_bs16000_gc2.yaml
@@ -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
\ No newline at end of file
diff --git a/egs/aishell/branchformer/run.sh b/egs/aishell/branchformer/run.sh
index 86c12b1..37336ea 100755
--- a/egs/aishell/branchformer/run.sh
+++ b/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
--
Gitblit v1.9.1