I am getting following error when the testing is being run. I am doing transfer learning and training have finished successfully and I am able to export the model too.
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&) threwFormatLoadException.
first non-empty line was “version https://git-lfs.github.com/spec/v1” not \data. Byte: 43
Fatal Python error: Aborted
Thread 0x00007fdfd3fff700 (most recent call first):
File “/usr/lib/python3.6/threading.py”, line 295 in wait
File “/usr/lib/python3.6/queue.py”, line 164 in get
File “/usr/local/lib/python3.6/dist-packages/tensorflow/python/summary/writer/event_file_writer.py”, line 159 in run
File “/usr/lib/python3.6/threading.py”, line 916 in _bootstrap_inner
File “/usr/lib/python3.6/threading.py”, line 884 in _bootstrap
Thread 0x00007fdfd2ffd700 (most recent call first):
File “/usr/lib/python3.6/threading.py”, line 295 in wait
File “/usr/lib/python3.6/queue.py”, line 164 in get
File “/usr/local/lib/python3.6/dist-packages/tensorflow/python/summary/writer/event_file_writer.py”, line 159 in run
File “/usr/lib/python3.6/threading.py”, line 916 in _bootstrap_inner
File “/usr/lib/python3.6/threading.py”, line 884 in _bootstrap
Current thread 0x00007fe0663e0740 (most recent call first):
File “/usr/local/lib/python3.6/dist-packages/ds_ctcdecoder/swigwrapper.py”, line 279 in init
File “/usr/local/lib/python3.6/dist-packages/ds_ctcdecoder/init.py”, line 30 in init
File “/root/sharedfolder/speech-recog/DeepSpeech-0.6.1/evaluate.py”, line 48 in evaluate
File “DeepSpeech.py”, line 684 in test
File “DeepSpeech.py”, line 951 in main
File “/usr/local/lib/python3.6/dist-packages/absl/app.py”, line 250 in _run_main
File “/usr/local/lib/python3.6/dist-packages/absl/app.py”, line 299 in run
File “DeepSpeech.py”, line 974 in
Aborted (core dumped)
I have tried installing git-lfs but no success. I have following configuration of DeepSpeech:
DeepSpeech Version: 0.6.1
Dataset used for transfer learning:
Source: https://voice.mozilla.org/en/datasets
Language: English
Version: en_1488h_2019-12-10
Please help me how I can resolve this issue.
Thanks,
Vishnu
Transfer learning is available in the current master branch, not 0.6. So switch to that and clone right with git lfs. Then use common voice or wait til the next release to get a model. You don’t have to build a scorer, look for kenlm.scorer in the repo and use run-tc-transfer.sh for settings on how to do transfer learning. All this works only in the current master branch.