| egs/librispeech_100h/conformer/conf/decode_asr_transformer_ctc0.3_beam5.yaml | ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史 | |
| egs/librispeech_100h/conformer/run.sh | ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史 |
egs/librispeech_100h/conformer/conf/decode_asr_transformer_ctc0.3_beam5.yaml
New file @@ -0,0 +1,6 @@ beam_size: 5 penalty: 0.0 maxlenratio: 0.0 minlenratio: 0.0 ctc_weight: 0.3 lm_weight: 0.0 egs/librispeech_100h/conformer/run.sh
@@ -53,7 +53,8 @@ asr_config=conf/train_asr_conformer.yaml model_dir="baseline_$(basename "${asr_config}" .yaml)_${lang}_${token_type}_${tag}" inference_config=conf/decode_asr_transformer_ctc0.3_beam1.yaml #inference_config=conf/decode_asr_transformer_ctc0.3_beam1.yaml inference_config=conf/decode_asr_transformer_ctc0.3_beam5.yaml #inference_config=conf/decode_asr_transformer_ctc0.3_beam20.yaml inference_asr_model=valid.acc.ave_10best.pb
