From a0843941281f833010157f8f8680fe7a1a8fc2dd Mon Sep 17 00:00:00 2001
From: yangyaming <mxscmxsc@gmail.com>
Date: Fri, 3 Nov 2017 14:52:10 +0800
Subject: [PATCH] Add doc and adjust some codes.

---
 data_utils/data.py | 4 ++--
 infer.py           | 4 +---
 test.py            | 4 +---
 tools/tune.py      | 4 +---
 4 files changed, 5 insertions(+), 11 deletions(-)

diff --git a/data_utils/data.py b/data_utils/data.py
index edd4047e..70ee6fba 100644
--- a/data_utils/data.py
+++ b/data_utils/data.py
@@ -103,8 +103,8 @@ class DataGenerator(object):
         :type filename: basestring | file
         :param transcript: Transcription text.
         :type transcript: basestring
-        :return: Tuple of audio feature tensor and list of token ids for
-                 transcription.
+        :return: Tuple of audio feature tensor and data of transcription part,
+                 where transcription part could be token ids or text.
         :rtype: tuple of (2darray, list)
         """
         if filename.startswith('tar:'):
diff --git a/infer.py b/infer.py
index 74524602..9ac3e632 100644
--- a/infer.py
+++ b/infer.py
@@ -103,9 +103,7 @@ def infer():
         num_processes=args.num_proc_bsearch)
 
     error_rate_func = cer if args.error_rate_type == 'cer' else wer
-    target_transcripts = [
-        transcript for _, transcript in infer_data
-    ]
+    target_transcripts = [transcript for _, transcript in infer_data]
     for target, result in zip(target_transcripts, result_transcripts):
         print("\nTarget Transcription: %s\nOutput Transcription: %s" %
               (target, result))
diff --git a/test.py b/test.py
index 5466f960..63fc4f65 100644
--- a/test.py
+++ b/test.py
@@ -104,9 +104,7 @@ def evaluate():
             vocab_list=vocab_list,
             language_model_path=args.lang_model_path,
             num_processes=args.num_proc_bsearch)
-        target_transcripts = [
-            transcript for _, transcript in infer_data
-        ]
+        target_transcripts = [transcript for _, transcript in infer_data]
         for target, result in zip(target_transcripts, result_transcripts):
             error_sum += error_rate_func(target, result)
             num_ins += 1
diff --git a/tools/tune.py b/tools/tune.py
index 99ffb5f5..966029a8 100644
--- a/tools/tune.py
+++ b/tools/tune.py
@@ -164,9 +164,7 @@ def tune():
             for i in xrange(len(infer_data))
         ]
 
-        target_transcripts = [
-            transcript for _, transcript in infer_data
-        ]
+        target_transcripts = [transcript for _, transcript in infer_data]
 
         num_ins += len(target_transcripts)
         # grid search