AISHELL-4

by Beijing Shell Shell Technology

120h Mandarin meeting corpus — multi-speaker conference-room scenarios.

TL;DR

120h Mandarin meeting corpus — multi-speaker conference-room scenarios.

Best for mandarin meeting transcription + diarization with 8-mic linear array. Pricing: free.

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

What it is

AISHELL-4 (OpenSLR-111) is 120 hours of Mandarin meeting recordings from a real conference room with an 8-channel linear microphone array. License: CC BY 4.0.

Best for: Mandarin meeting transcription + diarization with 8-mic linear array.
Watch out for: CC BY 4.0 · ~120h · 8-mic linear array recordings of 4–8-person meetings. Cite: Fu et al., Interspeech 2021.

Install / use

https://www.openslr.org/111/

Features

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

AISHELL-4 vs Whipscribe

FeatureAISHELL-4Whipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationYesYes
Word timestampsNoYes
StreamingNoNo
Languages199
PlatformsOpenSLRWeb, API, MCP

Alternatives to AISHELL-4

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.