PyLaia (human transcriptions + agreement-based split)
Reported on 4 benchmarks across 2 tasks · 1 paper · 4 SOTA
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Methodology2 results
- CER (%)· 2023-06-19SOTA5.57best: 4.34 (PyLaia (all transcriptions + agreement-based split))
- WER (%)· 2023-06-19SOTA19.12best: 15.14 (PyLaia (all transcriptions + agreement-based split))
Adversarial2 results
- CER (%)· 2023-06-19SOTA5.57best: 4.34 (PyLaia (all transcriptions + agreement-based split))
- WER (%)· 2023-06-19SOTA19.12best: 15.14 (PyLaia (all transcriptions + agreement-based split))