File size: 329 Bytes
5fa1a76
 
 
 
 
 
 
1
2
3
4
5
6
7
], dtype=float32),
 'path': '/root/.cache/huggingface/datasets/downloads/extracted/f14948e0e84be638dd7943ac36518a4cf3324e8b7aa331c5ab11541518e9368c/en-US~JOINT_ACCOUNT/602ba55abb1e6d0fbce92065.wav',
 'sampling_rate': 8000}

This returns three items:

array is the speech signal loaded - and potentially resampled - as a 1D array.