MLCommons Speech

by MLCommons

MLCommons Speech working group — People's Speech + MLPerf speech benchmarks.

Looking at MLCommons Speech? Try this first.

Drop your audio. Transcript in seconds. First transcript free, then $4 = 300 min

TL;DR

Best for industry-standard ASR training benchmarks + permissively-licensed data releases. Pricing: free.

Category
Open source
License
Apache-2.0
Stars
★ 115
Last push
2024-01-11
Pricing
free
Platforms
Web

What it is

MLCommons (formerly MLPerf) runs the speech working group that published People's Speech (30kh CC-BY) and the MLPerf ASR benchmarks.

Best for: Industry-standard ASR training benchmarks + permissively-licensed data releases.
Watch out for: Apache-2.0 + CC-BY-SA · industry consortium.

Install / use

Go to MLCommons Speech mlcommons.org

Features

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

Links

GitHub repo ↗

MLCommons Speech vs Whipscribe

FeatureMLCommons SpeechWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfree$4–$24 one-time packs (credits never expire) · $2 single unlock · 60 min free on signup
Speaker diarizationNoYes
Word timestampsNoYes
StreamingNoNo
Languages199
PlatformsWebWeb, API, MCP

Alternatives to MLCommons Speech

OpenAI Whisper
OpenAI

The reference open-source multilingual ASR model from OpenAI.

OSS · MIT ★ 107.0k
whisper.cpp
Georgi Gerganov

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

OSS · MIT ★ 52.8k
faster-whisper
SYSTRAN

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

OSS · MIT ★ 24.8k

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.