I am finetuning TrOCR and using Character Error Rate from jiwer as the metric. def compute_cer(pred_ids, label_ids, processor): pred_str = processor.batch_decode(pred_ids, skip_special_tokens=True) label_ids[label_ids == -100] = processor.tokenizer.pad_token_id print(f"len of label_ids …

TrOCR, CER metric error

nielsr December 9, 2021, 10:05am 2

I believe this was a bug that has been fixed, see Datasets.load_metric("cer") does not work

1 Like