from speechbrain.pretrained import EncoderDecoderASR
model = EncoderDecoderASR.from_hparams(
"Gastron/lp-initial-aed-short"
)
model.transcribe_file("file.wav")
CRDNN with Attention trained on LP
This is a an initial model, partly wrong configuration, just to show an initial example.
from speechbrain.pretrained import EncoderDecoderASR model = EncoderDecoderASR.from_hparams( "Gastron/lp-initial-aed-short" ) model.transcribe_file("file.wav")