From fc9a7b0f61cb5c5f59cb0e62c9c33890b4a13f0c Mon Sep 17 00:00:00 2001
From: Yibing Liu <liuyibing01@baidu.com>
Date: Fri, 29 Sep 2017 19:55:05 +0800
Subject: [PATCH] convert decoding results to unicode in DS2

---
 deep_speech_2/decoders/swig_wrapper.py   | 18 +++++++++++++-----
 deep_speech_2/examples/tiny/run_train.sh |  2 +-
 2 files changed, 14 insertions(+), 6 deletions(-)

diff --git a/deep_speech_2/decoders/swig_wrapper.py b/deep_speech_2/decoders/swig_wrapper.py
index 0a921125..21aed03c 100644
--- a/deep_speech_2/decoders/swig_wrapper.py
+++ b/deep_speech_2/decoders/swig_wrapper.py
@@ -35,7 +35,8 @@ def ctc_greedy_decoder(probs_seq, vocabulary):
     :return: Decoding result string.
     :rtype: basestring
     """
-    return swig_decoders.ctc_greedy_decoder(probs_seq.tolist(), vocabulary)
+    result = swig_decoders.ctc_greedy_decoder(probs_seq.tolist(), vocabulary)
+    return result.decode('utf-8')
 
 
 def ctc_beam_search_decoder(probs_seq,
@@ -69,9 +70,11 @@ def ctc_beam_search_decoder(probs_seq,
              results, in descending order of the probability.
     :rtype: list
     """
-    return swig_decoders.ctc_beam_search_decoder(probs_seq.tolist(), vocabulary,
-                                                 beam_size, cutoff_prob,
-                                                 cutoff_top_n, ext_scoring_func)
+    beam_results = swig_decoders.ctc_beam_search_decoder(
+        probs_seq.tolist(), vocabulary, beam_size, cutoff_prob, cutoff_top_n,
+        ext_scoring_func)
+    beam_results = [(res[0], res[1].decode('utf-8')) for res in beam_results]
+    return beam_results
 
 
 def ctc_beam_search_decoder_batch(probs_split,
@@ -111,6 +114,11 @@ def ctc_beam_search_decoder_batch(probs_split,
     """
     probs_split = [probs_seq.tolist() for probs_seq in probs_split]
 
-    return swig_decoders.ctc_beam_search_decoder_batch(
+    batch_beam_results = swig_decoders.ctc_beam_search_decoder_batch(
         probs_split, vocabulary, beam_size, num_processes, cutoff_prob,
         cutoff_top_n, ext_scoring_func)
+    batch_beam_results = [
+        [(res[0], res[1].decode("utf-8")) for res in beam_results]
+        for beam_results in batch_beam_results
+    ]
+    return batch_beam_results
diff --git a/deep_speech_2/examples/tiny/run_train.sh b/deep_speech_2/examples/tiny/run_train.sh
index 88b09bee..e03a8aff 100644
--- a/deep_speech_2/examples/tiny/run_train.sh
+++ b/deep_speech_2/examples/tiny/run_train.sh
@@ -33,7 +33,7 @@ python -u train.py \
 --shuffle_method='batch_shuffle_clipped'
 
 if [ $? -ne 0 ]; then
-    echo "Fail to do inference!"
+    echo "Fail in training!"
     exit 1
 fi
 
-- 
GitLab