birgermoell/wav2vec2-large-xlrs-estonian

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: "Fine-tuned facebook/wav2vec2-large-xlsr-53 in Luganda using the Common Voice" The model is evaluated as follows as follows on the Luganda test data of Common Voice. [Wav2Vec2-Large-XLSR-53-Estonian.], "We need to read the aduio files as arrays. Pre-processing the datasets. We need to use the model to predict the outcome of the test data. Preprocessing the dataset. We,