Tweeted By @soumithchintala
The speech team @ FAIR released wav2letter++:
— Soumith Chintala (@soumithchintala) December 21, 2018
- a fully convolutional speech recognition system
- a C++ ML library on top of ArrayFire
They recognized very early that C++ was their best option and dived in much before PyTorch C++ API existed.
See: https://t.co/mXmZ3d8Tab