#参考实现论文:Sequence Model with Self-Adaptive Sliding Window for Efficient Spoken Document Segmentation ，对ASR的结果进行段落分隔
batch_size 3 seq_num 16 max_sequence_len 64 dev acc:0.58 test f1:0.40
#参考实现论文:Sequence Model with Self-Adaptive Sliding Window for Efficient Spoken Document Segmentation ，对ASR的结果进行段落分隔
batch_size 3 seq_num 16 max_sequence_len 64 dev acc:0.58 test f1:0.40