CBHG model
Reported on 2 benchmarks across 1 task
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Speech2 results
- Diacritic Error Rate0.0113
- Word Error Rate (WER)0.0443
Reported on 2 benchmarks across 1 task
Note: results are matched by exact model name. Different papers may use the same name for different model variants.