RIRs and Noises (SLR28)

by JHU CLSP

Room impulse responses + isotropic noises — reverberation augmentation set.

TL;DR

Room impulse responses + isotropic noises — reverberation augmentation set.

Best for reverberation augmentation for far-field ASR + speaker verification. Pricing: free.

Category
Open source
License
—
Stars
—
Last push
—
Pricing
free
Platforms
OpenSLR

What it is

OpenSLR-28 bundles simulated + real RIRs + isotropic noise samples for far-field ASR data augmentation. The companion to MUSAN in Kaldi recipes. License: Apache-2.0.

Best for: Reverberation augmentation for far-field ASR + speaker verification.
Watch out for: Apache-2.0 · simulated + real RIRs · used in Kaldi recipes universally. Cite: Ko et al., ICASSP 2017.

Install / use

https://www.openslr.org/28/

Features

Speaker diarizationNo
Word-level timestampsNo
Streaming / real-timeNo
Languages supported0
HIPAA eligibleNo

RIRs and Noises (SLR28) vs Whipscribe

FeatureRIRs and Noises (SLR28)Whipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsNoYes
StreamingNoNo
Languages099
PlatformsOpenSLRWeb, API, MCP

Alternatives to RIRs and Noises (SLR28)

OpenAI Whisper
OpenAI

The reference open-source multilingual ASR model from OpenAI.

OSS · MIT ★ 98.1k
whisper.cpp
Georgi Gerganov

C/C++ port of Whisper — runs on anything, from a Raspberry Pi to Apple Silicon.

OSS · MIT ★ 48.8k
faster-whisper
SYSTRAN

4× faster than reference Whisper using CTranslate2 — production sweet spot.

OSS · MIT ★ 22.3k

Whipscribe is a managed faster-whisper + whisperX service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.