# Bengali-Loop: Community Benchmarks for Long-Form Bangla ASR and Speaker Diarization

arXiv: https://arxiv.org/abs/2602.14291 · HTML: https://mlsanity.com/paper/2602.14291/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Feb 2026.

## Built on by (most cited first, 7 of 7)

- [Make It Hard to Hear, Easy to Learn: Long-Form Bengali ASR and Speaker Diarization via Extreme Augmentation and Perfect Alignment](https://mlsanity.com/paper/2602.23070/) (2026)
- [Robust Long-Form Bangla Speech Processing: Automatic Speech Recognition and Speaker Diarization](https://mlsanity.com/paper/2602.21741/) (2026)
- [A Holistic Framework for Robust Bangla ASR and Speaker Diarization with Optimized VAD and CTC Alignment](https://mlsanity.com/paper/2602.22935/) (2026)
- [An Investigation Into Various Approaches For Bengali Long-Form Speech Transcription and Bengali Speaker Diarization](https://mlsanity.com/paper/2603.03158/) (2026)
- [WhisperAlign: Word-Boundary-Aware ASR and WhisperX-Anchored Pyannote Diarization for Long-Form Bengali Speech](https://mlsanity.com/paper/2603.04809/) (2026)
- [ShobdoSetu: A Data-Centric Framework for Bengali Long-Form Speech Recognition and Speaker Diarization](https://mlsanity.com/paper/2603.19256/) (2026)
- [Bangla-WhisperDiar: Fine-Tuning Whisper and PyAnnote for Bangla Long-Form Speech Recognition and Speaker Diarization](https://mlsanity.com/paper/2605.08214/) (2026)

## Abstract (arXiv)

Bengali (Bangla) remains under-resourced in long-form speech technology despite its wide use. We present Bengali-Loop, two community benchmarks to address this gap: (1) a long-form ASR corpus of 191 recordings (158.6 hours, 792k words) from 11 YouTube channels, collected via a reproducible subtitle-extraction pipeline and human-in-the-loop transcript verification; and (2) a speaker diarization corpus of 24 recordings (22 hours, 5,744 annotated segments) with fully manual speaker-turn labels in CSV format. Both benchmarks target realistic multi-speaker, long-duration content (e.g., Bangla drama/natok). We establish baselines (Tugstugi: 34.07% WER; pyannote.audio: 40.08% DER) and provide standardized evaluation protocols (WER/CER, DER), annotation rules, and data formats to support reproducible benchmarking and future model development for Bangla long-form ASR and diarization.