Command Palette
Search for a command to run...
语音识别
语音识别是将口语转换为文本的任务,涉及从音频记录中识别单词并将其转录为书面格式。其目标是在实时或录制音频中准确转录音频内容,同时考虑口音、语速和背景噪声等因素,以提高转录的准确性和可靠性。该技术在人机交互、自动字幕生成和语音助手等领域具有重要应用价值。
LibriSpeech test-clean
HuBERT with Libri-Light
LibriSpeech test-other
wav2vec 2.0 with Libri-Light
Switchboard + Hub500
TIMIT
wav2vec 2.0
AISHELL-1
Qwen-Audio
WSJ eval92
Common Voice German
wav2vec 2.0 XLS-R 1B + TEVR (5-gram)
swb_hub_500 WER fullSWBCH
TUDA
QuartzNet15x5DE (D37)
MediaSpeech
Quartznet
VietMed
SLUE
W2V2-B-VP100K
WenetSpeech
Paraformer-large
Common Voice French
ConformerCTC-L (5-gram)
Common Voice Spanish
ConformerCTC-L (4-gram)
GigaSpeech DEV
SAMBA ASR
Hub5'00 SwitchBoard
LAS + SpecAugment (with LM, Switchboard mild policy)
EasyCom
Libri-Light test-clean
CPC unlab-60k
Libri-Light test-other
CPC unlab-60k
GigaSpeech TEST
Zipformer+pruned transducer w/ CR-CTC
(no external language model)
LRS3-TED
Whisper
WSJ dev93
CTC-CRF ST-NAS
CHiME-6 dev_gss12
Tedlium
SPGISpeech
CHiME-6 eval
WSJ eval93
Deep Speech 2
Common Voice vi
Vietnamese end-to-end speech recognition using wav2vec 2.0 by VietAI
VIVOS
khanhld/chunkformer-large-vie
Fongbe audio
Triphone (39 features) + LDA and MLLT + SGMM
Speech Commands
Centaurus
Europarl-ASR EN Guest-test
AISHELL-2
AMI SDM1
AMI IMH
LibriCSS
TS-SEP
TED-LIUM
Whisper-LLaMa-7b
Common Voice English
Whisper (Large v2)
Common Voice Italian
Whisper (Large v2)
Europarl-ASR EN MEP-test
Common Voice
Common Voice Japanese
Switchboard (300hr)
Google Speech Commands - Musan
Switchboard SWBD
Common Voice Frisian
CAS-VSR-S101
GigaSpeech
Conformer/Transformer-AED
LibriSpeech train-clean-100 test-clean
wav2vec_wav2letter
AISHELL-2 Test IOS
AISHELL-2 Test Mic
Common Voice Portuguese
XLSR53 Wav2Vec2 Portuguese by Orlem Santos
Hub5'00 CallHome
Espresso
CALLHOME Spanish Speech
Common Voice Russian
Whisper (Large v2)
LibriSpeech 100h test-clean
Switchboard CallHome
LibriSpeech train-clean-100 test-other
wav2vec_wav2letter
facebook/multilingual_librispeech german
TDT 0-4
LRS2
RAVEn Large
Hub5'00 FISHER-SWBD
CTC-CRF
LibriSpeech 100h test-other
Branchformer + GFSA
CALLHOME En
WavLM Large & EEND-vector clustering
AISHELL-2 Test Android
Qwen-Audio
AISHELL-2 Android
Common Voice 8.0 Romansh Sursilvan
Common Voice 7.0 Hindi
Common Voice 8.0 Serbian
Common Voice Lithuanian
Mozilla Common Voice 16.1
SPGI Speech
Common Voice 8.0 Hindi
Common Voice Catalan
Common Voice Indonesian
Common Voice 8.0 German
Common Voice 7.0 Odia
Common Voice 8.0 Kazakh
Common Voice 7.0 Portuguese
Common Voice Maltese
Common Voice Georgian
Common Voice 8.0 Sorbian, Upper
Common Voice Odia
Common Voice 8.0 Kabyle
Robust Speech Event - Dev Data
Common Voice 7.0 Abkhaz
German ASR Data-Mix
Podlodka.io
fon
Common Voice 8.0 Hungarian
Common Voice Arabic
Common Voice Hindi
Reazonspeech
Common Voice 8.0 Central Kurdish
ATCOSIM corpus (Air Traffic Control Communications)
Common Voice Tamil
Common Voice 7.0 Arabic
Common Voice 8.0 Punjabi
Common Voice 8.0 Guarani
Common Voice 8.0 Bulgarian
Common Voice 8.0 Romansh Vallader
Common Voice 8.0 Uzbek
Robust Speech Event - Catalan Dev Data
Common Voice 8.0 Swahili
Common Voice 8.0 Breton
Common Voice 8.0 Erzya
Common Voice 8.0 Votic
MLS
Common Voice Persian
Common Voice Swedish
Common Voice 8.0 Maltese
Common Voice Breton
Common Voice Czech
UWB-ATCC dataset (Air Traffic Control Communications)
Common Voice Turkish
Common Voice 7.0 German
CORAA
tedlium-v3
AISHELL-2 Mic
Common Voice 8.0 Slovenian
Common Voice 7.0 Bashkir
Common Voice Dutch
Common Voice Welsh
Mozilla Common Voice 9.0
Common Voice 7.0 Votic
Common Voice 8.0 Basaa
projecte-aina/parlament_parla ca
Common Voice 8.0 Marathi
Common Voice 8.0 Hausa
Common Voice 8.0 Portuguese
ATCOSIM dataset (Air Traffic Control Communications)
Kazakh Speech Corpus v1.1
FLEURS
Russian LibriSpeech
Common Voice 8.0 Odia
Common Voice 8.0 Russian
Common Voice 8.0 French
Common Voice Polish
Common Voice 8.0 Kurmanji Kurdish
Common Voice 8.0 Assamese
Mozilla Common Voice 15.0 Persian
Common Voice 8.0 Galician
Common Voice Chinese (China)
Common Voice 8.0 Tatar
Common Voice Vietnamese
Common Voice 8.0 Santali (Ol Chiki)
Common Voice 8.0 Japanese
Common Voice 8.0 Dutch