On a new Quebec French benchmark, standard multilingual ASR benchmarks poorly predict real-world performance; the best open model reaches 8% WER while typical models sit near 14%.
Journal of Machine Learning Re- search, 25(97):1–52
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Benchmarking Large Pretrained Multilingual Models on Qu\'ebec French Speech Recognition
On a new Quebec French benchmark, standard multilingual ASR benchmarks poorly predict real-world performance; the best open model reaches 8% WER while typical models sit near 14%.