From 4a9dd1530c62a9d19d7491d6c2d1bd98bfd82574 Mon Sep 17 00:00:00 2001
From: Fangjun Kuang <csukuangfj@gmail.com>
Date: Fri, 5 Nov 2021 22:19:30 +0800
Subject: [PATCH] Remove duplicated token seq in rescoring.

---
 icefall/decode.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/icefall/decode.py b/icefall/decode.py
index 619b3267a..42622fa70 100644
--- a/icefall/decode.py
+++ b/icefall/decode.py
@@ -224,6 +224,7 @@ class Nbest(object):
         else:
             word_seq = lattice.aux_labels.index(path)
             word_seq = word_seq.remove_axis(word_seq.num_axes - 2)
+        word_seq = word_seq.remove_values_leq(0)
 
         # Each utterance has `num_paths` paths but some of them transduces
         # to the same word sequence, so we need to remove repeated word