Custom LM causes terrible false positive rate

Archives DeepSpeech
35
  1. Generate the LM from your text corpus.
  2. Generate the scorer package with LM above and any default alpha and beta values.
  3. Run lm_optimizer.py with your own data, fine tuning on LibriSpeech test does nothing to help your use case.
  4. At the end, regenerate the package with the new fine tuned alpha and beta values.