othrif/wav2vec_test

When using this model, make sure that your speech input is sampled at 16kHz . The model can be used directly (without a language model) as follows: import load_dataset, transformers and Wav2Vec2Processor . Make sure that the model is accurate . Fine-tuned facebook/wav2vec2-large-xlsr-53 in Egyptian using the arabicspeech.org MGB-3 using the Arabic_speech_corpus model . For example, the model was used to test a Facebook/Wav2vec2-Large-Xlsr in Egyptian . It can also be used to,