[Fisher] Issue on semisup/run_100k.sh

Hi,

I've come across two problems in the
`https://github.com/kaldi-asr/kaldi/blob/master/egs/fisher_english/s5/local/semisup/run_100k.sh` recipe.

1. On stage 7: When running `local/fisher_train_lms_pocolm.sh` I get an error becuase the number o n-grams of the dataset (100k) is smaller than the number of n-grams to prune:

```
the num-ngrams(1544907) of input LM is less than the target-num-ngrams(5000000), can not do any pruning.
```

2. On stage 10: the param `--sup-lat-dir $exp_root/chain/tri4a_train_sup_unk_lats` should be changed to `--sup-lat-dir $exp_root/chain/tri4a_train_sup_sp_unk_lats` which uses the `sp` version instead.

R,
Juan Pablo

Start with egs/fisher_english/s5/local/semisup/run_100k.sh and inspect stages 7 and 10, then trace the local/fisher_train_lms_pocolm.sh invocation. Reproduce the 100k recipe to confirm the language-model pruning failure and lattice-directory mismatch; done means both stages run with the intended 100k and supervised-speaker paths.

Written by the indexing model from the issue text.