| lj_speech = lj_speech.cast_column("audio", Audio(sampling_rate=16_000)) | |
| Load a processor with [AutoProcessor.from_pretrained]: | |
| from transformers import AutoProcessor | |
| processor = AutoProcessor.from_pretrained("facebook/wav2vec2-base-960h") | |
| Create a function to process the audio data contained in array to input_values, and tokenize text to labels. |