Reverb: Open-Source ASR and Diarization from Rev

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Bhandari, Nishchal, Chen, Danny, Fernández, Miguel Ángel del Río, Delworth, Natalie, Fox, Jennifer Drexler, Jetté, Migüel, McNamara, Quinten, Miller, Corey, Novotný, Ondřej, Profant, Ján, Qin, Nan, Ratajczak, Martin, Robichaud, Jean-Philippe
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917935448064000
author Bhandari, Nishchal
Chen, Danny
Fernández, Miguel Ángel del Río
Delworth, Natalie
Fox, Jennifer Drexler
Jetté, Migüel
McNamara, Quinten
Miller, Corey
Novotný, Ondřej
Profant, Ján
Qin, Nan
Ratajczak, Martin
Robichaud, Jean-Philippe
author_facet Bhandari, Nishchal
Chen, Danny
Fernández, Miguel Ángel del Río
Delworth, Natalie
Fox, Jennifer Drexler
Jetté, Migüel
McNamara, Quinten
Miller, Corey
Novotný, Ondřej
Profant, Ján
Qin, Nan
Ratajczak, Martin
Robichaud, Jean-Philippe
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_03930
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Reverb: Open-Source ASR and Diarization from Rev
Bhandari, Nishchal
Chen, Danny
Fernández, Miguel Ángel del Río
Delworth, Natalie
Fox, Jennifer Drexler
Jetté, Migüel
McNamara, Quinten
Miller, Corey
Novotný, Ondřej
Profant, Ján
Qin, Nan
Ratajczak, Martin
Robichaud, Jean-Philippe
Computation and Language
Sound
Audio and Speech Processing
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.
title Reverb: Open-Source ASR and Diarization from Rev
topic Computation and Language
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2410.03930