Deepspeech training

Question

i tried to run training for small data, using Mozilla DeepSpeech. All requirements are installed.

./bin/run-ldc93s1.sh

But i faced this problem:

 `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) 

Does anybody have any suggestions?

Thanks a lot!

• Yash Kumar Atri: You forgot to install git lfs
• Yash Kumar Atri: run this curl -s https://packagecloud.io/install/repositories/github/git-lfs/script.deb.sh | sudo bash and if error occurs use python3.6
• Dmitrii Li: Thank for your respond, but it's installed
• Yash Kumar Atri: using the INSTALL.sh script ?
• Dmitrii Li: Okay, got it. Thank you so much. I will check it.

Answer 1

Please validate the following once in your system:

1.Check git-lfs installed properly

2.Do proper checkout from github repository code and use appropriate models for the particular deepspeech version.