in normalizer/data_utils.py [0:0]
def get_text(sample):
if "text" in sample:
return sample["text"]
elif "sentence" in sample:
return sample["sentence"]
elif "normalized_text" in sample:
return sample["normalized_text"]
elif "transcript" in sample:
return sample["transcript"]
elif "transcription" in sample:
return sample["transcription"]
else:
raise ValueError(
f"Expected transcript column of either 'text', 'sentence', 'normalized_text' or 'transcript'. Got sample of "
".join{sample.keys()}. Ensure a text column name is present in the dataset."
)