Model average (#344)

* First upload of model average codes.

* minor fix

* update decode file

* update .flake8

* rename pruned_transducer_stateless3 to pruned_transducer_stateless4

* change epoch number counter starting from 1 instead of 0

* minor fix of pruned_transducer_stateless4/train.py

* refactor the checkpoint.py

* minor fix, update docs, and modify the epoch number to count from 1 in the pruned_transducer_stateless4/decode.py

* update author info

* add docs of the scaling in function average_checkpoints_with_averaged_model

Author: yaozengwei

.flake8

@@ -9,6 +9,7 @@ per-file-ignores =
     egs/tedlium3/ASR/*/conformer.py: E501,
     egs/gigaspeech/ASR/*/conformer.py: E501,
     egs/librispeech/ASR/pruned_transducer_stateless2/*.py: E501,
+    egs/librispeech/ASR/pruned_transducer_stateless4/*.py: E501,
     egs/librispeech/ASR/*/optim.py: E501,
     egs/librispeech/ASR/*/scaling.py: E501,
 

egs/librispeech/ASR/pruned_transducer_stateless4/__init__.py

@@ -0,0 +1 @@
+../pruned_transducer_stateless2/__init__.py

egs/librispeech/ASR/pruned_transducer_stateless4/asr_datamodule.py

@@ -0,0 +1 @@
+../pruned_transducer_stateless2/asr_datamodule.py

egs/librispeech/ASR/pruned_transducer_stateless4/beam_search.py

@@ -0,0 +1 @@
+../pruned_transducer_stateless2/beam_search.py

egs/librispeech/ASR/pruned_transducer_stateless4/conformer.py

@@ -0,0 +1 @@
+../pruned_transducer_stateless2/conformer.py