update the shell scripts

egs/aishell/asr/conf/base.yaml

@@ -6,13 +6,19 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1
 
-conv-kernel-sizes: 5,5
-conv-channels: 1024
+subsampling-type: conv1d
+subsmapling-layers: 2
+subsampling-filter: 2048
+subsampling-kernel: 5
+subsampling-stride: 2
+subsampling-norm: none
+subsampling-activation: glu
+
 dropout: 0.1
 activation-fn: relu
 encoder-embed-dim: 256

egs/aishell/asr/conf/big.yaml

@@ -6,13 +6,19 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 1e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1
 
-conv-kernel-sizes: 5,5
-conv-channels: 1024
+subsampling-type: conv1d
+subsmapling-layers: 2
+subsampling-filter: 2048
+subsampling-kernel: 5
+subsampling-stride: 2
+subsampling-norm: none
+subsampling-activation: glu
+
 dropout: 0.15
 activation-fn: relu
 encoder-embed-dim: 512

egs/aishell/asr/conf/conformer.yaml

 macaron-style: True
 use-cnn-module: True
 cnn-module-kernel: 31
+encoder-attention-type: rel_pos
+encoder-activation-fn: swish
\ No newline at end of file

egs/aishell/asr/conf/debug.yaml

@@ -23,13 +23,19 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1
 
-conv-kernel-sizes: 5,5
-conv-channels: 1024
+subsampling-type: conv1d
+subsmapling-layers: 2
+subsampling-filter: 2048
+subsampling-kernel: 5
+subsampling-stride: 2
+subsampling-norm: none
+subsampling-activation: glu
+
 dropout: 0.1
 activation-fn: relu
 encoder-embed-dim: 256

egs/aishell/asr/conf/pds_base.yaml

@@ -9,7 +9,7 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1

egs/aishell/asr/conf/pds_base_16.yaml

@@ -22,7 +22,7 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1

egs/aishell/asr/conf/pds_base_32.yaml

@@ -22,7 +22,7 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1

egs/aishell/asr/conf/pds_base_8.yaml

@@ -22,7 +22,7 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1

egs/aishell/asr/conf/pds_big_8.yaml

@@ -22,7 +22,7 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1

egs/libri_trans/asr/conf/debug.yaml

@@ -6,7 +6,7 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1

egs/libri_trans/asr/conf/pds_base.yaml

@@ -9,7 +9,7 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1

egs/libri_trans/asr/conf/pds_base_16.yaml

@@ -22,7 +22,7 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1

egs/libri_trans/asr/conf/pds_base_32.yaml

@@ -22,7 +22,7 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1

egs/libri_trans/asr/conf/pds_base_8.yaml

@@ -22,7 +22,7 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1

egs/libri_trans/st/conf/pds_base.yaml

@@ -9,7 +9,7 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1

egs/libri_trans/st/conf/pds_base_16.yaml

@@ -22,7 +22,7 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1

egs/libri_trans/st/conf/pds_base_32.yaml

@@ -22,7 +22,7 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1

egs/libri_trans/st/conf/pds_base_8.yaml

@@ -22,7 +22,7 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1

egs/libri_trans/st/conf/sate.yaml

+arch: s2t_sate
+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_with_ctc
+label_smoothing: 0.1
+
+encoder-normalize-before: True
+decoder-normalize-before: True
+
+subsampling-type: conv1d
+subsmapling-layers: 2
+subsampling-filter: 1024
+subsampling-kernel: 5
+subsampling-stride: 2
+subsampling-norm: none
+subsampling-activation: glu
+
+dropout: 0.1
+activation-fn: relu
+encoder-embed-dim: 256
+encoder-ffn-embed-dim: 2048
+encoder-layers: 12
+text-encoder-layers: 6
+decoder-layers: 6
+encoder-attention-heads: 4
+
+decoder-embed-dim: 256
+decoder-ffn-embed-dim: 2048
+decoder-attention-heads: 4
+
+acoustic-encoder: transformer
+adapter: league
+
+#load-pretrained-encoder-from:
+#load-pretrained-acoustic-encoder-from:
+#load-pretrained-text-encoder-from:
+#load-pretrained-decoder-from:
\ No newline at end of file

egs/libri_trans/st/conf/sate_big.yaml

+arch: s2t_sate
+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: 1e-3
+adam_betas: (0.9,0.98)
+
+criterion: label_smoothed_cross_entropy_with_ctc
+label_smoothing: 0.1
+
+encoder-normalize-before: True
+decoder-normalize-before: True
+
+subsampling-type: conv1d
+subsmapling-layers: 2
+subsampling-filter: 2048
+subsampling-kernel: 5
+subsampling-stride: 2
+subsampling-norm: none
+subsampling-activation: glu
+
+dropout: 0.15
+activation-fn: relu
+encoder-embed-dim: 512
+encoder-ffn-embed-dim: 2048
+encoder-layers: 12
+text-encoder-layers: 6
+decoder-layers: 6
+encoder-attention-heads: 8
+
+decoder-embed-dim: 512
+decoder-ffn-embed-dim: 2048
+decoder-attention-heads: 8
+
+acoustic-encoder: transformer
+adapter: league
+
+#load-pretrained-encoder-from:
+#load-pretrained-acoustic-encoder-from:
+#load-pretrained-text-encoder-from:
+#load-pretrained-decoder-from:
\ No newline at end of file

egs/libri_trans/st/conf/sate_big_pds.yaml

+arch: s2t_sate
+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: 1e-3
+adam_betas: (0.9,0.98)
+
+criterion: label_smoothed_cross_entropy_with_ctc
+label_smoothing: 0.1
+
+encoder-normalize-before: True
+decoder-normalize-before: True
+subsampling-type: conv1d
+subsmapling-layers: 2
+subsampling-filter: 2048
+subsampling-kernel: 5
+subsampling-stride: 2
+subsampling-norm: none
+subsampling-activation: glu
+
+dropout: 0.15
+activation-fn: relu
+encoder-ffn-embed-dim: 2048
+encoder-layers: 12
+text-encoder-layers: 6
+decoder-layers: 6
+encoder-attention-heads: 8
+
+decoder-embed-dim: 512
+decoder-ffn-embed-dim: 2048
+decoder-attention-heads: 8
+
+acoustic-encoder: pds
+adapter: league
+
+encoder-embed-dim: 512
+ctc-layer: 12
+pds-stages: 4
+pds-layers: 3_3_3_3
+pds-ratios: 2_2_1_2
+pds-fusion: True
+pds-fusion-method: all_conv
+pds-embed-dims: 512_512_512_512
+pds-ds-method: conv
+pds-embed-norm: True
+pds-position-embed: 1_1_1_1
+pds-kernel-sizes: 5_5_5_5
+pds-ffn-ratios: 4_4_4_4
+pds-attn-heads: 8_8_8_8
+
+#load-pretrained-encoder-from:
+#load-pretrained-acoustic-encoder-from:
+#load-pretrained-text-encoder-from:
+#load-pretrained-decoder-from:
\ No newline at end of file

egs/libri_trans/st/conf/sate_ctc.yaml → egs/libri_trans/st/conf/sate_pds.yaml

@@ -6,48 +6,31 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 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
 label_smoothing: 0.1
 
 encoder-normalize-before: True
 decoder-normalize-before: True
-
-subsampling-type: conv1d
-subsmapling-layers: 2
-subsampling-filter: 1024
-subsampling-kernel: 5
-subsampling-stride: 2
-subsampling-norm: none
-subsampling-activation: glu
-
 dropout: 0.1
 activation-fn: relu
-encoder-embed-dim: 256
 encoder-ffn-embed-dim: 2048
 encoder-layers: 12
 text-encoder-layers: 6
 decoder-layers: 6
 encoder-attention-heads: 4
 
-#load-pretrained-encoder-from:
-#load-pretrained-acoustic-encoder-from:
-#load-pretrained-text-encoder-from:
-#load-pretrained-decoder-from:
-
-#macaron-style: True
-#use-cnn-module: True
-#cnn-module-kernel: 31
+decoder-embed-dim: 256
+decoder-ffn-embed-dim: 2048
+decoder-attention-heads: 4
 
-#acoustic-encoder: pds
-acoustic-encoder: transformer
+acoustic-encoder: pds
 adapter: league
 
 encoder-embed-dim: 256
+ctc-layer: 12
 pds-stages: 4
-#pds-dropout: 0
 pds-layers: 3_3_3_3
 pds-ratios: 2_2_1_2
 pds-fusion: True
@@ -60,6 +43,7 @@ pds-kernel-sizes: 5_5_5_5
 pds-ffn-ratios: 8_8_8_8
 pds-attn-heads: 4_4_4_4
 
-decoder-embed-dim: 256
-decoder-ffn-embed-dim: 2048
-decoder-attention-heads: 4
\ No newline at end of file
+#load-pretrained-encoder-from:
+#load-pretrained-acoustic-encoder-from:
+#load-pretrained-text-encoder-from:
+#load-pretrained-decoder-from:
\ No newline at end of file

egs/librispeech/asr/conf/big.yaml

@@ -6,13 +6,19 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1
 
-conv-kernel-sizes: 5,5
-conv-channels: 1024
+subsampling-type: conv1d
+subsmapling-layers: 2
+subsampling-filter: 2048
+subsampling-kernel: 5
+subsampling-stride: 2
+subsampling-norm: none
+subsampling-activation: glu
+
 dropout: 0.15
 activation-fn: relu
 encoder-embed-dim: 512

egs/librispeech/asr/conf/conformer.yaml

 macaron-style: True
 use-cnn-module: True
 cnn-module-kernel: 31
-encoder-activation-fn: swish
-encoder-attention-type: rel_pos
\ No newline at end of file
+encoder-attention-type: rel_pos
+encoder-activation-fn: swish
\ No newline at end of file

egs/librispeech/asr/conf/pds_base.yaml

@@ -12,7 +12,7 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1

egs/librispeech/asr/conf/pds_base_16.yaml

@@ -22,7 +22,7 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1

egs/librispeech/asr/conf/pds_base_32.yaml

@@ -22,7 +22,7 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1

egs/librispeech/asr/conf/pds_base_8.yaml

@@ -22,7 +22,7 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1

egs/librispeech/asr/conf/pds_big.yaml

@@ -12,7 +12,7 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1

egs/librispeech/asr/conf/pds_big_16.yaml

@@ -22,7 +22,7 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1

egs/librispeech/asr/conf/pds_big_32.yaml

@@ -22,7 +22,7 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1

egs/librispeech/asr/conf/pds_big_8.yaml

@@ -21,7 +21,7 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1

egs/librispeech/asr/conf/pds_deep.yaml

@@ -12,7 +12,7 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1

egs/librispeech/asr/conf/pds_deep_16.yaml

@@ -22,7 +22,7 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1

egs/librispeech/asr/conf/pds_deep_32.yaml

@@ -22,7 +22,7 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1

egs/librispeech/asr/conf/pds_deep_8.yaml

@@ -22,7 +22,7 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1

egs/librispeech/asr/conf/purectc.yaml

@@ -5,13 +5,19 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: ctc
 post-process: sentencepiece
 
-conv-kernel-sizes: 5,5
-conv-channels: 1024
+subsampling-type: conv1d
+subsmapling-layers: 2
+subsampling-filter: 1024
+subsampling-kernel: 5
+subsampling-stride: 2
+subsampling-norm: none
+subsampling-activation: glu
+
 dropout: 0.1
 activation-fn: relu
 encoder-embed-dim: 256

egs/mustc/asr/conf/big.yaml

@@ -6,13 +6,19 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1
 
-conv-kernel-sizes: 5,5
-conv-channels: 1024
+subsampling-type: conv1d
+subsmapling-layers: 2
+subsampling-filter: 2048
+subsampling-kernel: 5
+subsampling-stride: 2
+subsampling-norm: none
+subsampling-activation: glu
+
 dropout: 0.15
 activation-fn: relu
 encoder-embed-dim: 512

egs/mustc/asr/conf/conformer.yaml

 macaron-style: True
 use-cnn-module: True
 cnn-module-kernel: 31
+encoder-attention-type: rel_pos
+encoder-activation-fn: swish

egs/mustc/asr/conf/pds_base.yaml

@@ -9,7 +9,7 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1

egs/mustc/asr/conf/pds_base_16.yaml

@@ -22,7 +22,7 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1

egs/mustc/asr/conf/pds_base_32.yaml

@@ -22,7 +22,7 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1

egs/mustc/asr/conf/pds_base_8.yaml

@@ -22,7 +22,7 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1

egs/mustc/asr/conf/pds_big_8.yaml

@@ -22,7 +22,7 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1

egs/mustc/st/conf/conformer.yaml

 macaron-style: True
 use-cnn-module: True
 cnn-module-kernel: 31
+encoder-attention-type: rel_pos
+encoder-activation-fn: swish
\ No newline at end of file

egs/mustc/st/conf/pds_base.yaml

@@ -9,7 +9,7 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1

egs/mustc/st/conf/pds_base_16.yaml

@@ -22,7 +22,7 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1

egs/mustc/st/conf/pds_base_32.yaml

@@ -22,7 +22,7 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1

egs/mustc/st/conf/pds_base_8.yaml

@@ -26,7 +26,7 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1

egs/mustc/st/conf/sate.yaml

@@ -6,15 +6,22 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1
 
 encoder-normalize-before: True
 decoder-normalize-before: True
-conv-kernel-sizes: 5,5
-conv-channels: 1024
+
+subsampling-type: conv1d
+subsmapling-layers: 2
+subsampling-filter: 1024
+subsampling-kernel: 5
+subsampling-stride: 2
+subsampling-norm: none
+subsampling-activation: glu
+
 dropout: 0.1
 activation-fn: relu
 encoder-embed-dim: 256

egs/mustc/st/conf/sate_big.yaml

@@ -6,15 +6,22 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 1e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1
 
 encoder-normalize-before: True
 decoder-normalize-before: True
-conv-kernel-sizes: 5,5
-conv-channels: 1024
+
+subsampling-type: conv1d
+subsmapling-layers: 2
+subsampling-filter: 2048
+subsampling-kernel: 5
+subsampling-stride: 2
+subsampling-norm: none
+subsampling-activation: glu
+
 dropout: 0.15
 activation-fn: relu
 encoder-embed-dim: 512

egs/mustc/st/conf/sate_big_pds.yaml

@@ -6,15 +6,21 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 1e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1
 
 encoder-normalize-before: True
 decoder-normalize-before: True
-conv-kernel-sizes: 5,5
-conv-channels: 1024
+subsampling-type: conv1d
+subsmapling-layers: 2
+subsampling-filter: 2048
+subsampling-kernel: 5
+subsampling-stride: 2
+subsampling-norm: none
+subsampling-activation: glu
+
 dropout: 0.15
 activation-fn: relu
 encoder-ffn-embed-dim: 2048

egs/mustc/st/conf/sate_pds.yaml

@@ -6,15 +6,13 @@ lr-scheduler: inverse_sqrt
 warmup-init-lr: 1e-7
 warmup-updates: 10000
 lr: 2e-3
-#adam_betas: (0.9,0.98)
+adam_betas: (0.9,0.98)
 
 criterion: label_smoothed_cross_entropy_with_ctc
 label_smoothing: 0.1
 
 encoder-normalize-before: True
 decoder-normalize-before: True
-conv-kernel-sizes: 5,5
-conv-channels: 1024
 dropout: 0.1
 activation-fn: relu
 encoder-ffn-embed-dim: 2048