从变压器加载预训练模型时,Unicode误差
我想为wav2vec使用预训练的模型,我从链接
tokenizer = Wav2Vec2Processor.from_pretrained('./wav2vec_small_960h.pt')
但是我有Unicode错误:
File "/Users/haochen/.pyenv/versions/3.10.1/lib/python3.10/codecs.py", line 322, in decode
(result, consumed) = self._buffer_decode(data, self.errors, final)
Unicodedecodeerror:'UTF-8'编解码器无法解码字节0x80位置0:无效启动字节
I would like to use the pre-trained model for wav2vec, I have downloaded the model from the link
tokenizer = Wav2Vec2Processor.from_pretrained('./wav2vec_small_960h.pt')
But I got the unicode error:
File "/Users/haochen/.pyenv/versions/3.10.1/lib/python3.10/codecs.py", line 322, in decode
(result, consumed) = self._buffer_decode(data, self.errors, final)
UnicodeDecodeError: 'utf-8' codec can't decode byte 0x80 in position 0: invalid start byte
如果你对这篇内容有疑问,欢迎到本站社区发帖提问 参与讨论,获取更多帮助,或者扫码二维码加入 Web 技术交流群。

绑定邮箱获取回复消息
由于您还没有绑定你的真实邮箱,如果其他用户或者作者回复了您的评论,将不能在第一时间通知您!
发布评论