The result of BLSTM is better than Transformer?

[DiLiangWU]

I run eend/egs/mini_librisppech/v1/run.sh and eend/egs/mini_librisppech/v1/local/run_blstm.sh, respectively. The result of run.sh (Transformer) is the same as RESULT.md (Final DER = 29.96%). However, the result of local/run_blstm.sh (BLSTM) is DER =17.02%, better than Transformer? Furthermore, I use CALLHOME corpora, the simulated mixtures are generated by SRE2008 and SWBD Cellular 1, the results also show that BLSTM is better than Transformer.

It is worth noting that a warning appears when i ran local/run_blstm.sh, as follows.

/workspace/EEND/tools/miniconda3/envs/eend/lib/python3.7/site-packages/chainer/iterators/multiprocess_iterator.py:629: UserWarning: Shared memory size is too small.
Please set shared_mem option for MultiprocessIterator.
Expect shared memory size: 4389780 bytes.
Actual shared memory size: 4171864 bytes.

I have no idea about this. And I'd like to know the results you got when running mini_librisppech/v1/local/run_blstm.sh.

Thank you very much.

[marccasals98]

The paper was published with BLSTMs in Transformers era, so it makes sense that is better this way. Also, it may be possible that Transformers need more data to perform better.