OpenEars 1.01


Bugfix update for the following three issues:

  1. Leaks in the dynamic language model generation process could crash the device,
  2. When using a very small model, the discounting method used by the language model generation process could occasionally result in certain words having a probability that is so low that it was equivalent to not having them in the model at all,
  3. There were 237 warnings during a device build due to unstripped local debug symbols, which had no effect on functionality but occluded useful warnings.