Merge pull request #256 from alibaba-damo-academy/dev_wjm

Dev wjm

funasr/bin/asr_inference_mfcca.py

@@ -41,8 +41,6 @@ from funasr.utils.types import str_or_none
 from funasr.utils import asr_utils, wav_utils, postprocess_utils
 import pdb
 
-header_colors = '\033[95m'
-end_colors = '\033[0m'
 
 global_asr_language: str = 'zh-cn'
 global_sample_rate: Union[int, Dict[Any, int]] = {

funasr/datasets/preprocessor.py

@@ -47,15 +47,11 @@ def forward_segment(text, dic):
 
 def seg_tokenize(txt, seg_dict):
     out_txt = ""
-    pattern = re.compile(r"([\u4E00-\u9FA5A-Za-z0-9])")
     for word in txt:
-        if pattern.match(word):
-            if word in seg_dict:
-                out_txt += seg_dict[word] + " "
-            else:
-                out_txt += "<unk>" + " "
+        if word in seg_dict:
+            out_txt += seg_dict[word] + " "
         else:
-            continue
+            out_txt += "<unk>" + " "
     return out_txt.strip().split()
 
 def seg_tokenize_wo_pattern(txt, seg_dict):

tests/test_asr_inference_pipeline.py

@@ -452,7 +452,7 @@ class TestUniasrInferencePipelines(unittest.TestCase):
     def test_uniasr_2pass_zhcn_16k_common_vocab8358_offline(self):
         inference_pipeline = pipeline(
             task=Tasks.auto_speech_recognition,
-            model='damo/speech_UniASauto_speech_recognitionR_asr_2pass-zh-cn-16k-common-vocab8358-tensorflow1-offline')
+            model='damo/speech_UniASR_asr_2pass-zh-cn-16k-common-vocab8358-tensorflow1-offline')
         rec_result = inference_pipeline(
             audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav',
             param_dict={"decoding_model": "offline"})