Using Wav2Vec 2.0 from HuggingFace and Fairseq with SpeechBrain

This tutorial describes how to combine (use and finetune) pretrained wav2vec2 models coming both from fairseq or HuggingFace. Any wav2vec 2.0 model trained with the fairseq toolkit or integrated to the transformers interface of HuggingFace can be then plugged to SpeechBrain to approach a speech-related task: automatic speech recognition, speaker recognition, spoken language understanding ...

Open in Google Colab

Complex and Quaternion Neural networks

This tutorial demonstrates how to use the SpeechBrain implementation of complex-valued and quaternion-valued neural networks for speech technologies. It covers the basics of highdimensional representations and the associated neural layers : Linear, Convolution, Recurrent and Normalisation.

Open in Google Colab

Recurrent Neural Networks and SpeechBrain

Recurrent Neural Networks (RNNs) offer a natural way to process sequences. This tutorial demonstrates how to use the SpeechBrain implementations of RNNs including LSTMs, GRU, RNN and LiGRU a specific recurrent cell designed for speech-related tasks. RNNs are at the core of many sequence to sequence models.

Open in Google Colab