Kelly Davis
Kelly Davis
@SalvorinFex Thanks! Currently we're planning on using the CC0 audio from [freesound](https://freesound.org/) along with using many random samples of the training set, at a lower in volume, to create a...
Models trained on data with such augmentations are in the process of being trained.
@zaptrem They are coming later.
- [x] Improve logo placement on left navigation - [x] Add Twitter link - [x] Get references to work without jekyll-scholar - [x] Switch TTS splashes - [ ] Write...
@rajateku6 This is suggesting a specific enhancement to the code. If you wish to train another KenLM language model please add your question to the [Discourse Forum](https://discourse.mozilla.org/c/deep-speech).
Adding this to the 1.0.0 project. This may get implemented there, and it may not dependent upon the LM work done there
We can consider this, but generally we're narrowly focused on STT.
@div5yesh A `contrib` repo is a reasonable idea. But the we still have to consider the bandwidth required for review and tests of `contrib` code and how`contrib` is updated across...
Same here, python 2.7 os x installed from pip