From 3cd3473bf7a3b41484baa86d9092248d78e7af39 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期五, 21 四月 2023 17:17:37 +0800
Subject: [PATCH] docs

---
 funasr/bin/asr_inference_uniasr.py |   10 +++++-----
 1 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/funasr/bin/asr_inference_uniasr.py b/funasr/bin/asr_inference_uniasr.py
index ac71538..35ecdc2 100644
--- a/funasr/bin/asr_inference_uniasr.py
+++ b/funasr/bin/asr_inference_uniasr.py
@@ -37,9 +37,6 @@
 from funasr.models.frontend.wav_frontend import WavFrontend
 
 
-header_colors = '\033[95m'
-end_colors = '\033[0m'
-
 
 class Speech2Text:
     """Speech2Text class
@@ -261,6 +258,7 @@
 
             # Change integer-ids to tokens
             token = self.converter.ids2tokens(token_int)
+            token = list(filter(lambda x: x != "<gbg>", token))
 
             if self.tokenizer is not None:
                 text = self.tokenizer.tokens2text(token)
@@ -381,6 +379,8 @@
         **kwargs,
 ):
     assert check_argument_types()
+    ncpu = kwargs.get("ncpu", 1)
+    torch.set_num_threads(ncpu)
     if batch_size > 1:
         raise NotImplementedError("batch decoding is not implemented")
     if word_lm_train_config is not None:
@@ -506,13 +506,13 @@
                     ibest_writer["score"][key] = str(hyp.score)
     
                 if text is not None:
-                    text_postprocessed, _ = postprocess_utils.sentence_postprocess(token)
+                    text_postprocessed, word_lists = postprocess_utils.sentence_postprocess(token)
                     item = {'key': key, 'value': text_postprocessed}
                     asr_result_list.append(item)
                     finish_count += 1
                     asr_utils.print_progress(finish_count / file_count)
                     if writer is not None:
-                        ibest_writer["text"][key] = text
+                        ibest_writer["text"][key] = " ".join(word_lists)
         return asr_result_list
     
     return _forward

--
Gitblit v1.9.1