AudioMAE

by Meta AI

Masked-Autoencoder pretrain for audio — feeds downstream ASR.

TL;DR

Masked-Autoencoder pretrain for audio — feeds downstream ASR.

Best for self-supervised audio pretraining baselines. Pricing: free.

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

What it is

The AudioMAE paper code. CC-BY-NC-4.0 — non-commercial.

Best for: Self-supervised audio pretraining baselines.
Watch out for: Research; not a turnkey ASR engine.

Install / use

git clone https://github.com/facebookresearch/AudioMAE

Features

Speaker diarizationNo
Word-level timestampsYes
Streaming / real-timeNo
Languages supported1
HIPAA eligibleNo

AudioMAE vs Whipscribe

FeatureAudioMAEWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsYesYes
StreamingNoNo
Languages199
PlatformsLinuxWeb, API, MCP

Alternatives to AudioMAE

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.