alokmatta/wav2vec2-large-xlsr-53-sw

The Wav2Vec2-Large-XLSR-53-Swahili model can be used directly (without a language model) When using this model, make sure that your speech input is sampled at 16kHz . The script used for training can be found here- Coming Soon! The test results are WIP % with torch.no_grad() and the test result is WIP . The model is based on the ALFFA, ... and ... dataset{s}. The model can also be used to train Swahili language models using the language model of Facebook/wav2vec2-large-xlsr-53 on Swahilian .,