Use 🤗 Datasets' [~datasets.Dataset.cast_column] method to upsample the sampling rate to 16kHz:

dataset = dataset.cast_column("audio", Audio(sampling_rate=16_000))

Call the audio column again to resample the audio file:

dataset[0]["audio"]
{'array': array([ 2.3443763e-05,  2.1729663e-04,  2.2145823e-04, ,
         3.8356509e-05, -7.3497440e-06, -2.1754686e-05], dtype=float32),
 'path': '/root/.cache/huggingface/datasets/downloads/extracted/f14948e0e84be638dd7943ac36518a4cf3324e8b7aa331c5ab11541518e9368c/en-US~JOINT_ACCOUNT/602ba55abb1e6d0fbce92065.wav',
 'sampling_rate': 16000}

Next, load a feature extractor to normalize and pad the input.