| title | Building a Production Greek-English Speech Recognizer |
|---|---|
| authors | Christos Petrocheilos, Cleopatra Papadopoulou, Chris Porikis, Ioakeim Perros, Ayoub Kirouane, Themistoklis Nikolis |
| date | 2026-09-11 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2609.13498 |
| affiliation | KIEFER |
| upvotes | 9 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | We report a multi-month engineering program to build Sophea, a production bilingual Greek-English automatic speech recognition system. We evaluate the system against nine production gates covering Greek and English word error rate, language identification, and hallucinations on non-speech audio. Across twenty-three training iterations and two model architectures, no training-data composition passed all nine gates simultaneously. Meeting the Greek noisy-environment target required about 1,500 steps of dense domain exposure, while preserving English language identification tolerated only about 250 steps, or about 1,250 with a rebalanced mix that reduced Greek accuracy. We describe a six-stage data pipeline in which calibrating an audio-quality filter against in-domain anchors reduced the discarded share of scored Greek audio from 98.7 percent to 10.6 percent. A pre-registered ablation isolated a hallucination defect to one training-data package. A three-model ROVER ensemble increased gate coverage from 4-7 of 9 for individual models to 9 of 9 and reduced overlapping-speech WER from 53.35 percent to 37.87 percent, a 29 percent relative improvement. A separate learned per-clip arbiter over two models is listed as sophea/asr-k1 (preview) on the public Open ASR Leaderboard, with 4.26 percent average WER across eight public English test sets, and reaches 25.88 percent WER on live Greek noisy-environment traffic. We also document five cases in which a measurement tool produced a plausible but incorrect result and seven substantial approaches that were evaluated but not shipped. No model weights or training data are released; we report methodology and quantitative results only. |
cite
@misc{petrocheilos2026building,
title={Building a Production Greek-English Speech Recognizer},
author={Christos Petrocheilos and Cleopatra Papadopoulou and Chris Porikis and Ioakeim Perros and Ayoub Kirouane and Themistoklis Nikolis},
year={2026},
eprint={2609.13498},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2609.13498}
}