listen-attend-and-spell and las
These are competitors, as both repositories provide independent TensorFlow implementations of the Listen, Attend and Spell model for Automatic Speech Recognition.
About listen-attend-and-spell
WindQAQ/listen-attend-and-spell
Tensorflow implementation of "Listen, Attend and Spell" authored by William Chan. This project utilizes input pipeline and estimator API of Tensorflow, which makes the training and evaluation truly end-to-end.
About las
ServerSideHannes/las
tf 2.0 implementation of Listen, attend and spell
This project offers a foundational building block for creating speech recognition systems. It takes raw audio represented as a mel spectrogram and a sequence of previously predicted tokens (like words or phonemes), then predicts the next token in the sequence. This is a tool for machine learning engineers and researchers working on spoken language understanding.
Scores updated daily from GitHub, PyPI, and npm data. How scores work