A Conformer-based Arabic ASR trained from scratch on 15,000 hours of weak labels outperforms several open and closed-source models on standard Arabic benchmarks.
On authorship authentication of arabic articles
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Advancing Arabic Speech Recognition Through Large-Scale Weakly Supervised Learning
A Conformer-based Arabic ASR trained from scratch on 15,000 hours of weak labels outperforms several open and closed-source models on standard Arabic benchmarks.