File size: 535 Bytes
752ce9b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 |
from dataset import Dataset
from model import Models
def data(dataset):
for i, item in enumerate(dataset):
yield {**item["audio"], "reference": item["norm_text"]}
def streamed_infernce(dataset, pipeline):
# placeholders for predictions and references
predictions = []
references = []
# run streamed inference
for out in pipeline(data(dataset), batch_size=16):
predictions.append(pipeline(out["text"]))
references.append(out["reference"][0])
return predictions, references |