yaml

egs/librispeech/asr/run.sh

@@ -192,7 +192,7 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
     cp -f ${pwd_dir}/`basename ${BASH_SOURCE[0]}` ${model_dir}
     cp -f ${pwd_dir}/train.sh ${model_dir}
 
-    train_config=${train_config},basis
+    train_config=basis,${train_config}
     config_list="${train_config//,/ }"
     idx=0
     for config in ${config_list[@]}

egs/mustc/st/conf/reproduction_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)
+
+ctc-weight: 0.3
+share-ctc-and-embed: True
+criterion: label_smoothed_cross_entropy_with_ctc
+label_smoothing: 0.1
+
+encoder-normalize-before: True
+decoder-normalize-before: True
+
+encoder-embed-norm: True
+encoder-no-scale-embedding: True
+textual-encoder-embed-norm: True
+textual-encoder-no-scale-embedding: True
+
+subsampling-type: conv1d
+subsampling-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: inter_league
+# adapter: none
+# adapter-embed-norm: True
+# adapter-out-norm: True
+
+# load-pretrained-encoder-from:
+# load-pretrained-acoustic-encoder-from:
+# load-pretrained-text-encoder-from:
+# load-pretrained-decoder-from:
\ No newline at end of file