Building Open Source Hugging Face Leaderboards - Koel Labs

by Ruslan Mukhamedvaleev

Sometimes, the best machine learning models are hidden in plain sight. During our work on phonemic transcription, we stumbled upon a specialized ginic model that had been fine-tuned on Facebook's XLSR-53 model using the Buckeye corpus. This discovery proved significant: Ginic performs 1.2x better than Facebook, and iterating on their approach, our model performs 2.2x better than ginic. Finding this model was more a product of extensive searching than systematic discovery, highlighting a broader challenge in the phoneme transcription space that led us to build this open-source leaderboard.