An implementation of Conformer: Convolution-augmented Transformer for Speech Recognition, a Transformer Variant in TensorFlow/Keras
ConformerBlock
implementation, now usable and no longer WIP in https://github.com/Rishit-dagli/Conformer/pull/9
Attention
class in https://github.com/Rishit-dagli/Conformer/pull/10
ConformerConvModule
and ConformerBlock
in https://github.com/Rishit-dagli/Conformer/pull/11
Full Changelog: https://github.com/Rishit-dagli/Conformer/compare/v0.1.0...v0.2.0
This is the initial release of Conformer and implements the Conformer (Convolution-augmented Transformer for Speech Recognition) as a subclassed TensorFlow model. Conformer achieves the best of both worlds (transformers for content-based global interactions and CNNs to exploit local features) by studying how to combine convolution neural networks and transformers to model both local and global dependencies of an audio sequence in a parameter-efficient way.
You would majorly want to follow the examples and use the ConformerConvModule
or ConformerBlock
classes.