Quartznet
Reported on 4 benchmarks across 1 task · 1 paper · 4 SOTA
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Audio4 results
- WER for Arabic· 2021-03-30SOTA0.13
- WER for French· 2021-03-30SOTA0.1915best: 0.1683 (Azure)
- WER for Spanish· 2021-03-30SOTA0.1826best: 0.0879 (Wit)
- WER for Turkish· 2021-03-30SOTA0.1422best: 0.0768 (Wit)