fix the implementation of the relative position encoding in conformer, optimize the code of ctc loss

I reformat the code, implement the intermedia ctc with adapter and the ctc decoding.

Cumulative updates. I mainly optimize the shell scripts and support the new benchmarks. It is more friendly to MT researchers (also including me). I also improve the code. Of course, old problems still remain and new problems arise. Just keep coding.

I optimize the implementation of the speech-to-text tasks. As always, I update the shell scripts and YAML configures for easy training.
There may be some bugs. So, the follow-up update is coming!