modify the shell scripts

egs/mustc/st/conf/train_ctc_enc_rpr.yaml → egs/mustc/st/conf/train_ctc_rpr.yaml

@@ -37,7 +37,10 @@ encoder-ffn-embed-dim: 2048
 encoder-layers: 12
 decoder-layers: 6
 encoder-attention-heads: 4
-encoder-attention-type: rel_selfattn
+
+encoder-attention-type: relative
+decoder-attention-type: relative
+max-relative-length: 20
 
 #decoder-embed-dim: 256
 #decoder-ffn-embed-dim: 2048

egs/mustc/st/conf/train_ctc_sate_rpr.yaml

+train-subset: train_st
+valid-subset: dev_st
+
+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-acoustic-encoder-from: /home/xuchen/st/checkpoints/mustc/asr/train_ctc_st_vocab/avg_10_checkpoint.pt
+#load-pretrained-text-encoder-from: /home/xuchen/st/checkpoints/mustc/mt/st_share10k_train_baseline/avg_10_checkpoint.pt
+#load-pretrained-decoder-from: /home/xuchen/st/checkpoints/mustc/mt/st_share10k_train_baseline/avg_10_checkpoint.pt
+
+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)
+
+ctc-weight: 0.3
+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-embed-dim: 256
+encoder-ffn-embed-dim: 2048
+encoder-layers: 12
+text-encoder-layers: 6
+decoder-layers: 6
+encoder-attention-heads: 4
+
+macaron-style: True
+use-cnn-module: True
+cnn-module-kernel: 31
+
+acoustic-encoder: transformer
+adapter: league
+
+encoder-attention-type: relative
+decoder-attention-type: relative
+max-relative-length: 20
+
+#decoder-embed-dim: 256
+#decoder-ffn-embed-dim: 2048
+#decoder-attention-heads: 4
+#attention-dropout: 0.1
+#activation-dropout: 0.1