Hokkien→En (Three-stage)

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

Speech-to-Speech TranslationonTAT
ASR-BLEU (Dev)· uses extra data
12.5
best: 13.6 (Hokkien→En (Two-pass decoding))
Speech-to-Speech TranslationonTAT
ASR-BLEU (Test)· uses extra data
8.8
best: 12.5 (Hokkien→En (Two-pass decoding))