config_mtl_asr_st_ctcst.yaml

target_unigram:
   decoder_type: transformer
   dict: /data/zhangshaolei/StreamSpeech/configs/fr-en/tgt_unigram6000/spm_unigram_fr.txt
   data: /data/zhangshaolei/StreamSpeech/configs/fr-en/tgt_unigram6000
   loss_weight: 8.0
   rdrop_alpha: 0.0
   decoder_args:
      decoder_layers: 4
      decoder_embed_dim: 512
      decoder_ffn_embed_dim: 2048
      decoder_attention_heads: 8
   label_smoothing: 0.1
source_unigram:
   decoder_type: ctc
   dict: /data/zhangshaolei/StreamSpeech/configs/fr-en/src_unigram6000/spm_unigram_fr.txt
   data: /data/zhangshaolei/StreamSpeech/configs/fr-en/src_unigram6000
   loss_weight: 4.0
   rdrop_alpha: 0.0
   decoder_args:
      decoder_layers: 0
      decoder_embed_dim: 512
      decoder_ffn_embed_dim: 2048
      decoder_attention_heads: 8
   label_smoothing: 0.1
ctc_target_unigram:
   decoder_type: ctc
   dict: /data/zhangshaolei/StreamSpeech/configs/fr-en/tgt_unigram6000/spm_unigram_fr.txt
   data: /data/zhangshaolei/StreamSpeech/configs/fr-en/tgt_unigram6000
   loss_weight: 4.0
   rdrop_alpha: 0.0
   decoder_args:
      decoder_layers: 0
      decoder_embed_dim: 512
      decoder_ffn_embed_dim: 2048
      decoder_attention_heads: 8
   label_smoothing: 0.1