自動音声認識（ASR）

LibriSpeech

FLEURS

SADA

MGB2

Gigaspeech

VoxPopuli

Common Voice 15.0

In-house Data

MGB3

MGB5

AISHELL

Spgispeech

AMI

Common Voice 17.0 TEST

FLEURS TEST

GigaSpeech 2 DEV

GigaSpeech 2 TEST

MASC

Common Voice

Bench

IH

SADA2022

unknown

VoxLRS-SA

LibriTTS

SlideSpeech

ArzEn

Earnings-22

LibriSpeech test.clean

LibriSpeech test.other

Librispeech-100h

Mixat

Seed-TTS

TED-LIUM

Tedlium

Tedlium2

TunSwitch

FS

Librispeech test-other

Lwazi

MCV-ACCENT-TEST

NCHTL

Wenetspeech

Casablanca

Ksponspeech

LRS2

MuAViC

Multilingual LibriSpeech

ReazonSpeech

Speech Command v2

Aishell-1

AMI test

Common Voice 17.0

Earnings22

emg2qwerty

ESB

Europarl-ASR EN Guest-test

GigaSpeech 2

Gigspeech

Libri-clean

Libri-other

Librispeech test-clean

LRW

TED-LIUM v3

Vuk’uzenzele isiXhosa Speech Dataset (ViXSD)

ALFAA

AMI-MDM

AMMI-LigAikuma

Arabic

CommonVoice17

CSL-Daily

DVoice

Ego4D

English

Europarl-ASR EN MEP-test

FKD

French

Hindi

How2

MCV-ACCENT

OpenBible

ParallelCorp (MULT)

PHOENIX14

PHOENIX14-T

SADA (SAU)

SlideASR-Bench

SlideASR-S

Synthetic LibriSpeech meetings

TARIC-SLU (TUN)

TAU Urban Acoustic Scenes 2019

TED

VisSpeech

Aishell test set

AIShell-3

AudioSet mixed with People's Speech and LibriSpeech

bibleTTS

Brain-to-Text '24 benchmark

British CS dataset

BuzzWord Test Set

CALLHOME Spanish Speech

CHiME-3

CHiME-3-Mix

CHiME-4

CHiME3 (Mixed)

CHiME3 (Single)

Chinese CS dataset

CMLR

CMU-Arctic

CommonVoice 17.0

CommonVoice 7.0 French

CORAA ASR

dev-clean

dev-other

facebook/multilingual_librispeech german

GigaSpeech-ESC50

Google Speech Commands V2 12

GRID

HEC

L2 Arctic

L2-Arctic

Librispeech-960h

LRS3

LRS3-TED

LS-C

MD-Easy

MD-Hard

MD-Long

MLC-SLM

Mozilla Common-Voice

MS-SNSD

MuPe Life Stories

Noizeus

NURC-SP Audio Corpus

SAA

SouthAfricaTTS

test meeting

test net

test-clean

test-other

UASpeech

VB-DEMAND

ViXSD

Word Form Variation Set