Fine-tuning XLS-R Wav2Vec2 model for Swahili Automatic Speech Recognition

Understanding Wav2Vec2 Wav2Vec2 is a pre-trained model for Automatic Speech Recognition (ASR) and was released in September 2020 by Alexei Baevski, Michael Auli, and Alex Conneau. Soon after the superior performance of Wav2Vec2 was demonstrated on on...