Question

我正在Mozilla深度语音中为印地语-英语混合语言设置端到端ASR。在训练深度语音时，我正在获取Unicode。错误

我点击了以下链接：https://github.com/JRMeyer/kyrgyz-voice-hackathon/blob/master/guides/deepspeech.txt

并据此设置环境。

cd DeepSpeech
# add paths to LANG/{train,dev,test}.csv in .compute
nano .compute 
bash .compute

Traceback (most recent call last):

      File "DeepSpeech.py", line 829, in <module>
        tf.app.run(main)
      File "/home/rohitk/tmp/venv/lib/python3.5/site-packages/tensorflow/python/platform/app.py", line 125, in run
        _sys.exit(main(argv))
      File "DeepSpeech.py", line 808, in main
        initialize_globals()
      File "/home/rohitk/DeepSpeech/util/config.py", line 64, in initialize_globals
        c.alphabet = Alphabet(os.path.abspath(FLAGS.alphabet_config_path))
      File "/home/rohitk/DeepSpeech/util/text.py", line 17, in __init__
        for line in fin:
      File "/home/rohitk/tmp/venv/lib/python3.5/codecs.py", line 711, in __next__
        return next(self.reader)
      File "/home/rohitk/tmp/venv/lib/python3.5/codecs.py", line 642, in __next__
        line = self.readline()
      File "/home/rohitk/tmp/venv/lib/python3.5/codecs.py", line 555, in readline
        data = self.read(readsize, firstline=True)
      File "/home/rohitk/tmp/venv/lib/python3.5/codecs.py", line 501, in read
        newchars, decodedbytes = self.decode(data, self.errors)
    UnicodeDecodeError: 'utf-8' codec can't decode byte 0x93 in position 0: invalid start byte

我希望测试能够成功培训。

UnicodeDecodeError：'utf-8'编解码器无法解码位置0的字节0x93：无效的起始字节

0 个答案: