Reverb: Open-Source ASR and Diarization from Rev
Not on the map. Why?
Abstract (arXiv)
Today, we are open-sourcing our core speech recognition and diarization models for non-commercial use. We are releasing both a full production pipeline for developers as well as pared-down research models for experimentation. Rev hopes that these releases will spur research and innovation in the fast-moving domain of voice technology. The speech recognition models released today outperform all existing open source speech recognition models across a variety of long-form speech recognition domains.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 8 of its 10 references that are in the map. First posted on arXiv 4 Oct 2024.
Builds on
8 of 10 references.
References · 8
- 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
- 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,657
- 2021GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audiocited by 399
- 2018Speaker Recognition from Raw Waveform with SincNetcited by 166
- 2023Powerset multi-class cross entropy loss for neural speaker diarizationcited by 111
- 2021Earnings-21: A Practical Benchmark for ASR in the Wildcited by 62
- 2019Joint Speech Recognition and Speaker Diarization via Sequence Transductioncited by 49
- 2021A Configurable Multilingual Model is All You Need to Recognize All Languagescited by 28
Built on by
Citing papers per year: 2025: 2; 2026: 1.
3 papers.