kaldi在做实时线上语音识别系统遇到问题

Question

kaldi在做实时线上语音识别系统的时候遇到如下问题

root@poweredge:/joanna/kaldi/egs/aishell/online_demo# ./run.sh 
Extracting the models and data ...
tar: online-data.tar.bz2：无法 open: 没有那个文件或目录
tar: Error is not recoverable: exiting now

  SIMULATED ONLINE DECODING - pre-recorded audio is used

  The (bigram) language model used to build the decoding graph was
  estimated on an audio book's text. The text in question is
  "King Solomon's Mines" (http://www.gutenberg.org/ebooks/2166).
  The audio chunks to be decoded were taken from the audio book read
  by John Nicholson(http://librivox.org/king-solomons-mines-by-haggard/)

  NOTE: Using utterances from the book, on which the LM was estimated
        is considered to be "cheating" and we are doing this only for
        the purposes of the demo.

  You can type "./run.sh --test-mode live" to try it using your
  own voice!

online-wav-gmm-decode-faster --verbose=1 --rt-min=0.8 --rt-max=0.85 --max-active=4000 --beam=12.0 --acoustic-scale=0.0769 scp:./work/input.scp online-data/models/tri1/final.mdl online-data/models/tri1/HCLG.fst online-data/models/tri1/words.txt 1:2:3:4:5 ark,t:./work/trans.txt ark,t:./work/ali.txt 
ERROR (online-wav-gmm-decode-faster[5.5.1068~1-59299]:Input():kaldi-io.cc:756) Error opening input stream online-data/models/tri1/final.mdl

[ Stack-Trace: ]
online-wav-gmm-decode-faster(kaldi::MessageLogger::LogMessage() const+0x6de) [0x5578b37b4c8c]
online-wav-gmm-decode-faster(kaldi::MessageLogger::LogAndThrow::operator=(kaldi::MessageLogger const&)+0x25) [0x5578b36aad89]
online-wav-gmm-decode-faster(kaldi::Input::Input(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool*)+0xbe) [0x5578b3746ef0]
online-wav-gmm-decode-faster(main+0x902) [0x5578b36a7ecb]
/lib/x86_64-linux-gnu/libc.so.6(+0x29d90) [0x7fcea1a29d90]
/lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0x80) [0x7fcea1a29e40]
online-wav-gmm-decode-faster(_start+0x25) [0x5578b36a7505]

kaldi::KaldiFatalError./run.sh: 行 101: online-data/audio/trans.txt: 没有那个文件或目录
compute-wer --mode=present ark,t:./work/ref.txt ark,t:./work/hyp.txt 
WARNING (compute-wer[5.5.1068~1-59299]:Open():util/kaldi-table-inl.h:513) Failed to open stream ./work/ref.txt
ERROR (compute-wer[5.5.1068~1-59299]:SequentialTableReader():util/kaldi-table-inl.h:860) Error constructing TableReader: rspecifier is ark,t:./work/ref.txt

[ Stack-Trace: ]
compute-wer(kaldi::MessageLogger::LogMessage() const+0x6de) [0x561b6ccdc9b8]
compute-wer(kaldi::MessageLogger::LogAndThrow::operator=(kaldi::MessageLogger const&)+0x25) [0x561b6cc5ce41]
compute-wer(kaldi::SequentialTableReader<kaldi::TokenVectorHolder>::SequentialTableReader(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)+0xc4) [0x561b6cc620e6]
compute-wer(main+0x1ea) [0x561b6cc5bd73]
/lib/x86_64-linux-gnu/libc.so.6(+0x29d90) [0x7f1834a29d90]
/lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0x80) [0x7f1834a29e40]
compute-wer(_start+0x25) [0x561b6cc5bac5]

Answer 1

该回答通过自己思路及引用到GPTᴼᴾᴱᴺᴬᴵ搜索,得到内容具体如下：

根据输出的错误信息，可以看出在运行时遇到了两个问题：

1. "tar: online-data.tar.bz2：无法 open: 没有那个文件或目录"，这个错误提示说明在从压缩文件中提取数据和模型时出现了问题。可能是由于文件不存在或路径错误导致的。需要检查一下路径和文件名是否正确，并且确认文件是否存在。

2. "ERROR (online-wav-gmm-decode-faster[5.5.1068~1-59299]:Input():kaldi-io.cc:756) Error opening input stream online-data/models/tri1/final.mdl"，这个错误提示说明在运行识别程序时无法打开模型文件。这可能是由于文件不存在、权限不足或路径错误导致的。需要检查一下模型文件路径和名称是否正确，并且确认文件是否存在。

另外，还有一些警告和错误提示，如 "行 101: online-data/audio/trans.txt: 没有那个文件或目录" 和 "WARNING (compute-wer[5.5.1068~1-59299]:Open():util/kaldi-table-inl.h:513) Failed to open stream ./work/ref.txt"，这些提示也需要检查文件路径和名称是否正确，并且确认文件是否存在。

---

如果以上回答对您有所帮助，点击一下采纳该答案～谢谢