optimize the shell script

egs/librispeech/asr/conf/train_ctc.yaml → egs/librispeech/asr/conf/ctc.yaml

-train-subset: train_st
-valid-subset: dev_st
+train-subset: train-clean-100,train-clean-360,train-other-500
+valid-subset: dev-clean
 
 
-max-epoch: 50
-max-update: 100000
+max-epoch: 100
+max-update: 300000
 
 
 num-workers: 8
 num-workers: 8
 patience: 10
 patience: 10

egs/mustc/asr/conf/pyramid.yaml

+arch: pys2t_transformer_s
+encoder-embed-dim: 512
+pyramid-stages: 4
+pyramid-layers: 2_3_5_2
+pyramid-sr-ratios: 2_2_2_2
+pyramid-embed-dims: 64_128_256_512
+pyramid-reduced-embed: conv
+pyramid-embed-norm: True
+pyramid-position-embed: 1_0_0_0
+pyramid-kernel-sizes: 5_5_5_5
+pyramid-ffn-ratios: 4_4_4_4
+pyramid-heads: 1_2_4_8
+
+train-subset: train_asr
+valid-subset: dev_asr
+
+max-epoch: 50
+max-update: 100000
+
+num-workers: 8
+patience: 10
+no-progress-bar: True
+log-interval: 100
+seed: 1
+report-accuracy: True
+
+#load-pretrained-encoder-from:
+#load-pretrained-decoder-from:
+
+share-decoder-input-output-embed: True
+optimizer: adam
+clip-norm: 10.0
+lr-scheduler: inverse_sqrt
+warmup-init-lr: 1e-7
+warmup-updates: 10000
+lr: 2e-3
+#adam_betas: (0.9,0.98)
+
+criterion: label_smoothed_cross_entropy
+label_smoothing: 0.1
+
+conv-channels: 1024
+dropout: 0.1
+activation-fn: relu
+encoder-ffn-embed-dim: 2048
+encoder-layers: 12
+decoder-layers: 6
+encoder-attention-heads: 4
+
+decoder-embed-dim: 256
+decoder-ffn-embed-dim: 2048
+decoder-attention-heads: 4
+attention-dropout: 0.1
+activation-dropout: 0.1

egs/librispeech/asr/conf/train_ctc_rpr.yaml → egs/mustc/asr/conf/pyramid_stage3.yaml

-train-subset: train_st
-valid-subset: dev_st
+arch: pys2t_transformer_s
+encoder-embed-dim: 512
+pyramid-stages: 3
+pyramid-layers: 3_6_3
+pyramid-sr-ratios: 2_2_2
+pyramid-embed-dims: 128_256_512
+pyramid-reduced-embed: conv
+pyramid-embed-norm: True
+pyramid-position-embed: 1_0_0
+pyramid-kernel-sizes: 5_5_5
+pyramid-ffn-ratios: 8_8_4
+pyramid-heads: 2_4_8
+
+train-subset: train_asr
+valid-subset: dev_asr
 
 
 max-epoch: 50
 max-epoch: 50
 max-update: 100000
 max-update: 100000
@@ -14,7 +27,6 @@ report-accuracy: True
 #load-pretrained-encoder-from:
 #load-pretrained-encoder-from:
 #load-pretrained-decoder-from:
 #load-pretrained-decoder-from:
 
 
-arch: s2t_transformer_s
 share-decoder-input-output-embed: True
 share-decoder-input-output-embed: True
 optimizer: adam
 optimizer: adam
 clip-norm: 10.0
 clip-norm: 10.0
@@ -24,25 +36,17 @@ warmup-updates: 10000
 lr: 2e-3
 lr: 2e-3
 #adam_betas: (0.9,0.98)
 #adam_betas: (0.9,0.98)
 
 
-ctc-weight: 0.3
-criterion: label_smoothed_cross_entropy_with_ctc
+criterion: label_smoothed_cross_entropy
 label_smoothing: 0.1
 label_smoothing: 0.1
 
 
-conv-kernel-sizes: 5,5
 conv-channels: 1024
 conv-channels: 1024
 dropout: 0.1
 dropout: 0.1
 activation-fn: relu
 activation-fn: relu
-encoder-embed-dim: 256
 encoder-ffn-embed-dim: 2048
 encoder-ffn-embed-dim: 2048
 encoder-layers: 12
 encoder-layers: 12
 decoder-layers: 6
 decoder-layers: 6
 encoder-attention-heads: 4
 encoder-attention-heads: 4
 
 
-encoder-attention-type: relative
-decoder-attention-type: relative
-max-encoder-relative-length: 100
-max-decoder-relative-length: 20
-
 decoder-embed-dim: 256
 decoder-embed-dim: 256
 decoder-ffn-embed-dim: 2048
 decoder-ffn-embed-dim: 2048
 decoder-attention-heads: 4
 decoder-attention-heads: 4

egs/librispeech/asr/conf/train_ctc_conformer.yaml → egs/mustc/st/conf/pyramid.yaml

+arch: pys2t_transformer_s
+#conv-kernel-sizes: 5
+encoder-embed-dim: 512
+pyramid-layers: 3_6_9
+ctc-layer: 7
+
 train-subset: train_st
 train-subset: train_st
 valid-subset: dev_st
 valid-subset: dev_st
 
 
@@ -14,7 +20,6 @@ report-accuracy: True
 #load-pretrained-encoder-from:
 #load-pretrained-encoder-from:
 #load-pretrained-decoder-from:
 #load-pretrained-decoder-from:
 
 
-arch: s2t_conformer_s
 share-decoder-input-output-embed: True
 share-decoder-input-output-embed: True
 optimizer: adam
 optimizer: adam
 clip-norm: 10.0
 clip-norm: 10.0
@@ -28,20 +33,14 @@ ctc-weight: 0.3
 criterion: label_smoothed_cross_entropy_with_ctc
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1
 label_smoothing: 0.1
 
 
-conv-kernel-sizes: 5,5
 conv-channels: 1024
 conv-channels: 1024
 dropout: 0.1
 dropout: 0.1
 activation-fn: relu
 activation-fn: relu
-encoder-embed-dim: 256
 encoder-ffn-embed-dim: 2048
 encoder-ffn-embed-dim: 2048
 encoder-layers: 12
 encoder-layers: 12
 decoder-layers: 6
 decoder-layers: 6
 encoder-attention-heads: 4
 encoder-attention-heads: 4
 
 
-macaron-style: True
-use-cnn-module: True
-cnn-module-kernel: 31
-
 decoder-embed-dim: 256
 decoder-embed-dim: 256
 decoder-ffn-embed-dim: 2048
 decoder-ffn-embed-dim: 2048
 decoder-attention-heads: 4
 decoder-attention-heads: 4