python - 深度语音训练

Question

我尝试使用 Mozilla DeepSpeech 对小数据进行训练。所有要求均已安装。

./bin/run-ldc93s1.sh

但是我遇到了这个问题:

    `Loading the LM will be faster if you build a binary file.
Reading data/lm/lm.binary
----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100
terminate called after throwing an instance of 'lm::FormatLoadException'
  what():  ../kenlm/lm/read_arpa.cc:65 in void lm::ReadARPACounts(util::FilePiece&, std::vector<long unsigned int>&) threw FormatLoadException.
first non-empty line was "version https://git-lfs.github.com/spec/v1" not \data\. Byte: 43
Fatal Python error: Aborted

Thread 0x00007f98e2033700 (most recent call first):
  File "/home/AU/li_d/miniconda3/lib/python3.7/threading.py", line 296 in wait
  File "/home/AU/li_d/miniconda3/lib/python3.7/queue.py", line 170 in get
  File "/home/AU/li_d/Desktop/env/lib/python3.7/site-packages/tensorflow/python/summary/writer/event_file_writer.py", line 159 in run
  File "/home/AU/li_d/miniconda3/lib/python3.7/threading.py", line 926 in _bootstrap_inner
  File "/home/AU/li_d/miniconda3/lib/python3.7/threading.py", line 890 in _bootstrap

Thread 0x00007f98e2834700 (most recent call first):
  File "/home/AU/li_d/miniconda3/lib/python3.7/threading.py", line 296 in wait
  File "/home/AU/li_d/miniconda3/lib/python3.7/queue.py", line 170 in get
  File "/home/AU/li_d/Desktop/env/lib/python3.7/site-packages/tensorflow/python/summary/writer/event_file_writer.py", line 159 in run
  File "/home/AU/li_d/miniconda3/lib/python3.7/threading.py", line 926 in _bootstrap_inner
  File "/home/AU/li_d/miniconda3/lib/python3.7/threading.py", line 890 in _bootstrap

Current thread 0x00007f99ed0ab740 (most recent call first):
  File "/home/AU/li_d/Desktop/env/lib/python3.7/site-packages/ds_ctcdecoder/swigwrapper.py", line 279 in init
  File "/home/AU/li_d/Desktop/env/lib/python3.7/site-packages/ds_ctcdecoder/__init__.py", line 30 in __init__
  File "/home/AU/li_d/Desktop/DeepSpeech2/evaluate.py", line 48 in evaluate
  File "DeepSpeech.py", line 675 in test
  File "DeepSpeech.py", line 942 in main
  File "/home/AU/li_d/Desktop/env/lib/python3.7/site-packages/absl/app.py", line 250 in _run_main
  File "/home/AU/li_d/Desktop/env/lib/python3.7/site-packages/absl/app.py", line 299 in run
  File "DeepSpeech.py", line 965 in <module>
Aborted (core dumped) 

有人有什么建议吗？

非常感谢!

Answer 1

请在您的系统中验证以下内容:

1.检查git-lfs是否安装正确

2.从 github 存储库代码中进行正确的 check out ，并针对特定的 Deepspeech 版本使用适当的模型。