{"url":"/dataset/common-voice","name":"Common Voice","full_name":"Common Voice","description_markdown":"**Common Voice** is an audio dataset that consists of a unique MP3 and corresponding text file. There are 9,283 recorded hours in the dataset. The dataset also includes demographic metadata like age, sex, and accent. The dataset consists of 7,335 validated hours in 60 languages.","description_withheld":null,"homepage":"https://commonvoice.mozilla.org","introduced_date":"2019-12-13","introduced_date_note":null,"introduced_by":{"paper":"/paper/common-voice-a-massively-multilingual-speech","title":"Common Voice: A Massively-Multilingual Speech Corpus","first_author":"Rosana Ardila","url":null},"license":{"name":"CC0","url":"https://creativecommons.org/share-your-work/public-domain/cc0/"},"modalities":[{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Speech Recognition","url":"/task/speech-recognition","datasets_with_task":"/datasets/task/speech-recognition"},{"name":"Automatic Speech Recognition","url":"/task/automatic-speech-recognition-2","datasets_with_task":"/datasets/task/automatic-speech-recognition-2"},{"name":"Audio Classification","url":"/task/audio-classification","datasets_with_task":"/datasets/task/audio-classification"},{"name":"Few-Shot Audio Classification","url":"/task/few-shot-audio-classification","datasets_with_task":"/datasets/task/few-shot-audio-classification"},{"name":"Language Identification","url":"/task/language-identification","datasets_with_task":"/datasets/task/language-identification"},{"name":"License Plate Detection","url":"/task/license-plate-detection","datasets_with_task":"/datasets/task/license-plate-detection"},{"name":"Cross-Lingual ASR","url":"/task/cross-lingual-asr","datasets_with_task":"/datasets/task/cross-lingual-asr"},{"name":"Speech-to-Text","url":"/task/speech-to-text","datasets_with_task":"/datasets/task/speech-to-text"},{"name":"speech-recognition","url":"/task/speech-recognition-1","datasets_with_task":"/datasets/task/speech-recognition-1"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"French","url":"/datasets/language/french"},{"name":"Spanish","url":"/datasets/language/spanish"},{"name":"German","url":"/datasets/language/german"},{"name":"Italian","url":"/datasets/language/italian"},{"name":"Chinese","url":"/datasets/language/chinese"},{"name":"Japanese","url":"/datasets/language/japanese"},{"name":"Russian","url":"/datasets/language/russian"},{"name":"Portuguese","url":"/datasets/language/portuguese"},{"name":"Arabic","url":"/datasets/language/arabic"},{"name":"Basque","url":"/datasets/language/basque"},{"name":"Breton","url":"/datasets/language/breton"},{"name":"Bulgarian","url":"/datasets/language/bulgarian"},{"name":"Catalan","url":"/datasets/language/catalan"},{"name":"Czech","url":"/datasets/language/czech"},{"name":"Dutch","url":"/datasets/language/dutch"},{"name":"Estonian","url":"/datasets/language/estonian"},{"name":"Finnish","url":"/datasets/language/finnish"},{"name":"Hindi","url":"/datasets/language/hindi"},{"name":"Hungarian","url":"/datasets/language/hungarian"},{"name":"Indonesian","url":"/datasets/language/indonesian"},{"name":"Irish","url":"/datasets/language/irish"},{"name":"Kazakh","url":"/datasets/language/kazakh"},{"name":"Latvian","url":"/datasets/language/latvian"},{"name":"Lithuanian","url":"/datasets/language/lithuanian"},{"name":"Maltese","url":"/datasets/language/maltese"},{"name":"Persian","url":"/datasets/language/persian"},{"name":"Polish","url":"/datasets/language/polish"},{"name":"Romanian","url":"/datasets/language/romanian"},{"name":"Slovak","url":"/datasets/language/slovak"},{"name":"Slovenian","url":"/datasets/language/slovenian"},{"name":"Swedish","url":"/datasets/language/swedish"},{"name":"Tamil","url":"/datasets/language/tamil"},{"name":"Thai","url":"/datasets/language/thai"},{"name":"Turkish","url":"/datasets/language/turkish"},{"name":"Ukrainian","url":"/datasets/language/ukrainian"},{"name":"Vietnamese","url":"/datasets/language/vietnamese"},{"name":"Welsh","url":"/datasets/language/welsh"},{"name":"Greek","url":"/datasets/language/greek"},{"name":"Mandarin Chinese","url":"/datasets/language/mandarin-chinese"},{"name":"Assamese","url":"/datasets/language/assamese"},{"name":"Chuvash","url":"/datasets/language/chuvash"},{"name":"Hakha Chin","url":"/datasets/language/hakha-chin"},{"name":"Dhivehi","url":"/datasets/language/dhivehi"},{"name":"Esperanto","url":"/datasets/language/esperanto"},{"name":"Kabyle","url":"/datasets/language/kabyle"},{"name":"Georgian","url":"/datasets/language/georgian"},{"name":"Kinyarwanda","url":"/datasets/language/kinyarwanda"},{"name":"Mongolian","url":"/datasets/language/mongolian"},{"name":"Odia","url":"/datasets/language/odia"},{"name":"Punjabi","url":"/datasets/language/punjabi"},{"name":"Tatar","url":"/datasets/language/tatar"},{"name":"Votic","url":"/datasets/language/votic"}],"variants":["Common Voice","Common Voice Tamil","Common Voice Welsh","Common Voice Swedish","Common Voice Portuguese","Common Voice Russian","Common Voice Odia","Common Voice Indonesian","Common Voice Finnish","Common Voice Hungarian","Common Voice Chinese (Hong Kong)","Common Voice Romanian","Common Voice Irish","Common Voice Latvian","Common Voice Greek","Common Voice Polish","Common Voice Spanish","Common Voice Turkish","Common Voice Thai","Common Voice Dhivehi","Common Voice Hindi","Common Voice Mongolian","Common Voice Chinese (Taiwan)","Common Voice Breton","Common Voice Basque","Common Voice Georgian","Common Voice Ukrainian","Common Voice Slovenian","Common Voice Luganda","Common Voice Assamese","Common Voice Maltese","Common Voice Persian","Common Voice Punjabi","Common Voice Kyrgyz","Common Voice Dutch","Common Voice Tatar","Common Voice Czech","Common Voice Estonian","Common Voice Sakha","Common Voice Vietnamese","Common Voice Frisian","Common Voice German","Common Voice Lithuanian","Common Voice Sorbian, Upper","Common Voice Interlingua","Common Voice Hakha Chin","Common Voice Esperanto","Common Voice Chuvash","Common Voice Arabic","Common Voice Romansh Vallader","Common Voice Italian","Common Voice Romansh Sursilvan","Common Voice French","Common Voice Catalan","Common Voice Japanese","Common Voice Chinese (China)","Common Voice Kinyarwanda","Common Voice English","Common Voice vi","Urdu","Punjabi","Common Voice ar","common-voice-7","common-voice","Common Voice 7","Common Voice 8","Common Voice Corpus 8.0","Common Voice Corpus 7.0","common_voice","mozilla-foundation/common_voice_8_0 es","Common Voice 6.1","Common Voice 7.0","Common Voice 8.0","Common Voice-7.0","Common Voice-8.0","mozilla-foundation/common_voice_8_0","Common Voice 8 NL","mozilla-foundation/common_voice_8_0 ca","Common Voice tr","mozilla-foundation/common_voice_7_0 es","Common Voice Abkhaz","common_voice es","Common Voice 7.0 Thai","Common Voice 7.0 Swedish","Common Voice 7.0 Bashkir","Common Voice 7.0 Hindi","Common Voice 7.0 Odia","Common Voice 7.0 Assamese","Common Voice 7.0 Urdu","Common Voice 7.0 Ukrainian","Common Voice 8.0 Swedish","Common Voice 7.0 Vietnamese","Common Voice 8.0 Kurmanji Kurdish","Common Voice 8.0 Punjabi","Common Voice 7.0 Finnish","Common Voice 7.0 Arabic","Common Voice 7.0 Spanish","Common Voice 7.0 Basaa","Common Voice 7.0 German","Common Voice 7.0 Breton","Common Voice 8.0 Central Kurdish","Common Voice 8.0 Hindi","Common Voice 8.0 Catalan","Common Voice 8.0 Chuvash","Common Voice 7.0 Bulgarian","Common Voice 7.0 Kyrgyz","Common Voice 7.0 Latvian","Common Voice 8.0 German","Common Voice 8.0 Armenian","Common Voice 7.0 Abkhaz","Common Voice 7.0 Armenian","Common Voice 7.0 Chuvash","Common Voice 7.0 Mongolian","Common Voice 7.0 Romansh Vallader","Common Voice 8.0 Irish","Common Voice 8.0 Swahili","Common Voice 8.0 Hungarian","Common Voice 8.0 French","Common Voice 8.0 Japanese","Common Voice 8.0 Dutch","Common Voice 8.0 Odia","Common Voice 8.0 Bulgarian","Common Voice 8.0 Marathi","Common Voice 8.0 Urdu","Common Voice 8.0 Latvian","Common Voice 8.0 Georgian","Common Voice 8.0 Czech","Common Voice 8.0 Slovak","Common Voice 7.0 Italian","Common Voice Galician","Common Voice 8.0 Italian","Common Voice 7.0 Georgian","Common Voice 7.0 Greek","Common Voice 7.0 Hausa","Common Voice 7.0 Hungarian","Common Voice 7.0 Irish","Common Voice 7.0 Kurmanji Kurdish","Common Voice 7.0 Lithuanian","Common Voice 7.0 Maltese","Common Voice 7.0 Romanian","Common Voice 7.0 Romansh Sursilvan","Common Voice 7.0 Sakha","Common Voice 7.0 Slovak","Common Voice 7.0 Slovenian","Common Voice 8.0 Indonesian","Common Voice 7.0 Uyghur","Common Voice 8.0 Uyghur","Common Voice 7.0 Russian","Common Voice 7.0 Turkish","Common Voice 8.0 Spanish","Common Voice 8.0 Finnish","Common Voice 8.0 Dhivehi","Common Voice 8.0 Estonian","Common Voice 8.0 Polish","Common Voice 7.0 Welsh","Common Voice 8.0 Portuguese","Common Voice 7.0 Indonesian","Common Voice 8.0 Ukrainian","Common Voice 8.0 Maltese","Common Voice 8.0 Romanian","Common Voice 8.0 Slovenian","Common Voice 8.0 Lithuanian","Common Voice 7.0 Tatar","Common Voice 8.0 Mongolian","Common Voice 8.0 Bashkir","Common Voice 7.0 Punjabi","Common Voice 8.0 Hausa","Common Voice 8.0 Turkish","Common Voice 8.0 Basaa","Common Voice 8.0 Tatar","Common Voice 8.0 Abkhaz","Common Voice 8.0 Assamese","Common Voice 8.0 Kyrgyz","Common Voice 8.0 Breton","Common Voice 7.0 Estonian","Common Voice 8.0 Sakha","Common Voice 8.0 Sorbian, Upper","Common Voice 7.0 French","Common Voice 8.0 Uzbek","Common Voice 7.0 Japanese","Common Voice 8.0 Greek","Common Voice 8.0 Interlingua","Common Voice 8.0 Romansh Sursilvan","Common Voice 7.0 Chinese (Hong Kong)","Common Voice 8.0 Romansh Vallader","Common Voice 8.0 Chinese (Hong Kong)","Common Voice 7.0 Portuguese","Common Voice 8.0 Vietnamese","Common Voice 8.0 Kabyle","Common Voice 8.0 English","Common Voice 8.0 Russian","Common Voice 8.0 Santali (Ol Chiki)","Common Voice 8.0 Erzya","Common Voice 8.0 Basque","Common Voice 8.0 Arabic","Common Voice 7.0 Esperanto","Common Voice 7.0 Chinese (China)","Common Voice 8.0 Serbian","Common Voice 7.0 Basque","Common Voice 8.0 Guarani","Common Voice 8.0 Votic","Common Voice 7.0 Luganda","Common Voice 7.0 Votic","Common Voice 8.0 Galician","Common Voice 7.0 Galician","Common Voice 8.0 Kazakh","Common Voice 7.0 Guarani","Common Voice 8.0 Belarusian","Common Voice 9.0 Urdu","Common Voice 9.0 Finnish","Common Voice 9.0 Marathi","Common Voice 9.0 Odia","Common Voice 9.0 Hindi","Mozilla Common Voice 7.0","Mozilla Common Voice 8.0","Common Voice 9.0 Swedish","CommonVoice 6.1 (French)","Common Voice 9.0 German","MCV 7.0","common-voice-7-0-german","common-voice-7-0-6","Mozilla Common Voice 9.0","common-voice-7-0","Mozilla Common Voice 8.0 test","Mozilla Common Voice 8.0 dev","Mozilla Common Voice 9.0 test","Mozilla Common Voice 9.0 dev","Mozilla Common Voice 10.0 test","Mozilla Common Voice 10.0 dev","Mozilla Common Voice 10.0","Common Voice 9.0 French","common-voice-11-0","mozilla-10","CommonVoice Corpus 10.0/ (German)","Mozilla Common Voice 11.0","Mozilla Common Voice 11.0 (Test)","Mozilla Common Voice 11.0 (Dev)","mozilla-foundation/common_voice_11_0 hi","Mozilla Common Voice 10.0 (Test)","Mozilla Common Voice 10.0 (Dev)","mozilla-foundation/common_voice_11_0 es","mozilla-foundation/common_voice_11_0 vi","COMMON_VOICE - VI","mozilla-foundation/common_voice_11_0 cs","mozilla-foundation/common_voice_11_0 pt","mozilla-foundation/common_voice_11_0 fi","mozilla-foundation/common_voice_11_0 tr","mozilla-foundation/common_voice_11_0 el","mozilla-foundation/common_voice_11_0 sv-SE","mozilla-foundation/common_voice_11_0 mr","mozilla-foundation/common_voice_11_0 id","mozilla-foundation/common_voice_11_0 as","mozilla-foundation/common_voice_11_0 ja","mozilla-foundation/common_voice_11_0 it","mozilla-foundation/common_voice_11_0 sk","mozilla-foundation/common_voice_11_0","mozilla-foundation/common_voice_11_0 pa-IN","common_voice_11_0","mozilla-foundation/common_voice_11_0 zh-HK","mozilla-foundation/common_voice_11_0 eu","mozilla-foundation/common_voice_10_0 uk","mozilla-foundation/common_voice_11_0 th","mozilla-foundation/common_voice_11_0 nl","mozilla-foundation/common_voice_11_0 ru","mozilla-foundation/common_voice_11_0 ka","mozilla-foundation/common_voice_11_0 ur","mozilla-foundation/common_voice_11_0 fy-NL","mozilla-foundation/common_voice_11_0 fa","mozilla-foundation/common_voice_11_0 fr","mozilla-foundation/common_voice_11_0 sl","mozilla-foundation/common_voice_11_0 kab","mozilla-foundation/common_voice_11_0 cy","mozilla-foundation/common_voice_11_0 de","mozilla-foundation/common_voice_11_0 tt","mozilla-foundation/common_voice_11_0 ca","mozilla-foundation/common_voice_11_0 ro","mozilla-foundation/common_voice_11_0 ta","mozilla-foundation/common_voice_11_0 be","mozilla-foundation/common_voice_11_0 bn","mozilla-foundation/common_voice_11_0 zh-CN","mozilla-foundation/common_voice_11_0 zh-TW","ERR2020, Common Voice 11.0, FLEURS","mozilla-foundation/common_voice_11_0 ba","mozilla-foundation/common_voice_11_0 np-NP","mozilla-foundation/common_voice_11_0 ml","mozilla-foundation/common_voice_9_0","mozilla-foundation/common_voice_11_0 az","mozilla-foundation/common_voice_11_0 sw","CommonVoice 7.0 (Spanish)","mozilla-foundation/common_voice_11_0 da","mozilla-foundation/common_voice_11_0 or","mozilla-foundation/common_voice_11_0 rw","mozilla-foundation/common_voice_11_0 gl","mozilla-foundation/common_voice_11_0 lv","mozilla-foundation/common_voice_11_0 hu","Common Voice (Urdu)","CommonVoice (clean)","CommonVoice (EL), CSS10 (EL)","mozilla-foundation/common_voice_11_0,facebook/voxpopuli,google/fleurs de,de,de_de","mozilla-foundation/common_voice_11_0,google/fleurs sr,sr_rs","MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - DE","mozilla-foundation/common_voice_13_0 th","mozilla-foundation/common_voice_16_0 yue","Mozilla Common Voice 16.1","Danish Common Voice 17","Common Voice 16.1","common-voice-17-0","Mozilla Common Voice","mozilla-foundation/common_voice_13_0 pt","common-voice-12-0","mozilla-foundation/common_voice_12_0","mozilla-foundation/common_voice_11_0 ha","mozilla-foundation/common_voice_11_0 bg","CommonVoice 10.0 (Mongolian)","Mozilla Common Voice 15.0 Persian","Mozilla Common Voice 6.1","MCV17","mozilla-foundation/common_voice_11_0 nan-tw","Mozilla Common Voice 12.0 (Urdu)","CommonVoice 10.0 (Persian)","mozilla-foundation/common_voice_13_0 ca","mozilla-foundation/common_voice_13_0 es","Mozilla Common Voice 17.0 (Test)","Mozilla Common Voice 17.0 (Dev)","MCV11 test","CommonVoice 10.0 (Arabic)","CommonVoice 10.0 (Farsi)","Common Voice (Galician)","Common Voice (French)","mozilla-foundation/common_voice_17_0 ar","mozilla-foundation/common_voice_13_0 gl","Common Voice 1.0 French","Common Voice 1.0 English","Mozilla Common Voice 17.0","Common Voice (Bengali)","mozilla-foundation/common_voice_17_0 pt","Common Voice (Swahili)"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/2Jyq/common_voice_21_0","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/eldad-akhaumere/common_voice_16_0","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/eldad-akhaumere/common_voice_16_0_","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/xi0v/c-v","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/common_voice","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mozilla-foundation/common_voice_5_1","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mozilla-foundation/common_voice_7_0","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/anton-l/common_voice_7_0_test","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/anton-l/common_voice_7_0_test1","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/anton-l/common_voice_1_0","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mozilla-foundation/common_voice_4_0","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mozilla-foundation/common_voice_1_0","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mozilla-foundation/common_voice_2_0","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mozilla-foundation/common_voice_3_0","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mozilla-foundation/common_voice_5_0","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mozilla-foundation/common_voice_6_0","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mozilla-foundation/common_voice_6_1","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/phongdtd/custom_common_voice","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mozilla-foundation/common_voice_8_0","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/HuggingFaceM4/common_voice","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mozilla-foundation/common_voice_9_0","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/JoesSattle/common_voice_specific_version","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/bengaliAI/CommonVoiceBangla","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mozilla-foundation/common_voice_10_0","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/taqwa92/cm.trial","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/TaahaIqbal/Paysys","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/reach-vb/common_voice_12_0","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mozilla-foundation/common_voice_12_0","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/KoddaDuck/Cylonix_ASR_dataset","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/reach-vb/common_voice_13_0","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mozilla-foundation/common_voice_13_0","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/gogogogo-1/test","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mariosasko/test_push_split","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/afern24/common_voice_13_0_dv_preprocessed","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/fmagot01/common_voice_13_0_dv_preprocessed","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/ssahir/common_voice_13_0_dv_preprocessed","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/artyomboyko/common_voice_13_0_ru","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/artyomboyko/common_voice_15_0_ru","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mozilla-foundation/common_voice_15_0","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/reach-vb/common_voice_16_1","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mozilla-foundation/common_voice_16_1","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/reach-vb/common_voice_14_0","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/artyomboyko/common_voice_15_0_RU","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mozilla-foundation/common_voice_14_0","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/z1amez/fresh","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/reach-vb/common_voice_16_0","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mozilla-foundation/common_voice_16_0","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/offbeatPickle/medical","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/reach-vb/common_voice_17","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/VingeNie/common_voice_16_1_zh_CN","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Seon25/hausa_2_to_eng","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Seon25/hausa_2_eng_2","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Seon25/common_voice_16_0","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/legacy-datasets/common_voice","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/ferno22/common_voice_13_0_dv_preprocessed","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Seon25/common_voice_16_0_","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Moosieus/commonvoice_17_0_en_codec2","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/dlxjj/common_voice_17_0","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/eldad-akhaumere/hausa_2_eng_2","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/common_voice","frameworks":["tf","jax"]},{"repo":"https://github.com/pytorch/audio","url":"https://pytorch.org/audio/stable/datasets.html#torchaudio.datasets.COMMONVOICE","frameworks":["pytorch"]},{"repo":"https://gitlab.com/jaco-assistant/corcua","url":"https://gitlab.com/jaco-assistant/corcua","frameworks":[]}],"num_papers_in_archive":449,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/speech-recognition-on-common-voice-german","task":"Speech Recognition","dataset_variant":"Common Voice German","rows":14,"metrics":["Test WER","Test CER"],"first_row_in_archive_order":{"model":"wav2vec 2.0 XLS-R 1B + TEVR (5-gram)","paper":"/paper/tevr-improving-speech-recognition-by-token","metrics":{"Test CER":"1.54%","Test WER":"3.64%"},"code_links":[{"title":"DeutscheKI/tevr-asr-tool","url":"https://github.com/DeutscheKI/tevr-asr-tool"},{"title":"fxtentacle/wav2vec2-xls-r-1b-tevr","url":"https://huggingface.co/fxtentacle/wav2vec2-xls-r-1b-tevr"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-french","task":"Speech Recognition","dataset_variant":"Common Voice French","rows":8,"metrics":["Test WER"],"first_row_in_archive_order":{"model":"ConformerCTC-L (5-gram)","paper":"/paper/scribosermo-fast-speech-to-text-models-for","metrics":{"Test WER":"8.13%"},"code_links":[{"title":"Jaco-Assistant/deepspeech-polyglot","url":"https://gitlab.com/Jaco-Assistant/deepspeech-polyglot"},{"title":"jaco-assistant/scribosermo","url":"https://gitlab.com/jaco-assistant/scribosermo"},{"title":"jaco-assistant/corcua","url":"https://gitlab.com/jaco-assistant/corcua"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-spanish","task":"Speech Recognition","dataset_variant":"Common Voice Spanish","rows":8,"metrics":["Test WER","Test CER","Test CER (+LM)","Test WER (+LM)"],"first_row_in_archive_order":{"model":"ConformerCTC-L (4-gram)","paper":"/paper/nemo-a-toolkit-for-building-ai-applications","metrics":{"Test WER":"5.5%"},"code_links":[{"title":"NVIDIA/NeMo","url":"https://github.com/NVIDIA/NeMo"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/few-shot-audio-classification-on-common-voice","task":"Few-Shot Audio Classification","dataset_variant":"Common Voice","rows":3,"metrics":["Top-1 Accuracy(5-Way-1-Shot)"],"first_row_in_archive_order":{"model":"MT-SLVR (SimCLR + MLAP) w/ Parallel Adapters (FSD50K, RN18)","paper":"/paper/mt-slvr-multi-task-self-supervised-learning","metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"35.22±0.40"},"code_links":[{"title":"cheggan/mt-slvr","url":"https://github.com/cheggan/mt-slvr"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-vi","task":"Speech Recognition","dataset_variant":"Common Voice vi","rows":3,"metrics":["Test WER"],"first_row_in_archive_order":{"model":"khanhld/chunkformer-large-vie","paper":"/paper/chunkformer-masked-chunking-conformer-for-1","metrics":{"Test WER":"6.66"},"code_links":[{"title":"khanld/chunkformer","url":"https://github.com/khanld/chunkformer"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-2","task":"Speech Recognition","dataset_variant":"Common Voice","rows":2,"metrics":["Test WER"],"first_row_in_archive_order":{"model":"ConformerXXL-P + Downstream NST","paper":"/paper/bigssl-exploring-the-frontier-of-large-scale","metrics":{"Test WER":"7.7%"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-english","task":"Speech Recognition","dataset_variant":"Common Voice English","rows":2,"metrics":["Word Error Rate (WER)","Test WER"],"first_row_in_archive_order":{"model":"parakeet-rnnt-1.1b","paper":"/paper/fast-conformer-with-linearly-scalable","metrics":{"Word Error Rate (WER)":"5.8%"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-italian","task":"Speech Recognition","dataset_variant":"Common Voice Italian","rows":2,"metrics":["Test WER"],"first_row_in_archive_order":{"model":"Whisper (Large v2)","paper":"/paper/robust-speech-recognition-via-large-scale-1","metrics":{"Test WER":"7.1%"},"code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"openai/whisper","url":"https://github.com/openai/whisper"},{"title":"ggerganov/whisper.cpp","url":"https://github.com/ggerganov/whisper.cpp"},{"title":"m-bain/whisperx","url":"https://github.com/m-bain/whisperx"},{"title":"sanchit-gandhi/whisper-jax","url":"https://github.com/sanchit-gandhi/whisper-jax"},{"title":"whisperspeech/whisperspeech","url":"https://github.com/whisperspeech/whisperspeech"},{"title":"collabora/whisperspeech","url":"https://github.com/collabora/whisperspeech"},{"title":"collabora/whisperlive","url":"https://github.com/collabora/whisperlive"},{"title":"kadirnar/whisper-plus","url":"https://github.com/kadirnar/whisper-plus"},{"title":"k2-fsa/icefall","url":"https://github.com/k2-fsa/icefall"},{"title":"briansidp/whisperbiasing","url":"https://github.com/briansidp/whisperbiasing"},{"title":"audioshake/alt-eval","url":"https://github.com/audioshake/alt-eval"},{"title":"robflynnyh/long-context-asr","url":"https://github.com/robflynnyh/long-context-asr"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/1/whisper"},{"title":"open-creator/icefall","url":"https://github.com/open-creator/icefall"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-frisian","task":"Speech Recognition","dataset_variant":"Common Voice Frisian","rows":1,"metrics":["Test WER"],"first_row_in_archive_order":{"model":"wav2vec2-large-xls-r-1b-frisian","paper":"/paper/improving-the-previous-state-of-the-art","metrics":{"Test WER":"15.99%"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-japanese","task":"Speech Recognition","dataset_variant":"Common Voice Japanese","rows":1,"metrics":["Test WER","Test CER"],"first_row_in_archive_order":{"model":"Whisper (Large v2)","paper":"/paper/robust-speech-recognition-via-large-scale-1","metrics":{"Test WER":"9.1%"},"code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"openai/whisper","url":"https://github.com/openai/whisper"},{"title":"ggerganov/whisper.cpp","url":"https://github.com/ggerganov/whisper.cpp"},{"title":"m-bain/whisperx","url":"https://github.com/m-bain/whisperx"},{"title":"sanchit-gandhi/whisper-jax","url":"https://github.com/sanchit-gandhi/whisper-jax"},{"title":"whisperspeech/whisperspeech","url":"https://github.com/whisperspeech/whisperspeech"},{"title":"collabora/whisperspeech","url":"https://github.com/collabora/whisperspeech"},{"title":"collabora/whisperlive","url":"https://github.com/collabora/whisperlive"},{"title":"kadirnar/whisper-plus","url":"https://github.com/kadirnar/whisper-plus"},{"title":"k2-fsa/icefall","url":"https://github.com/k2-fsa/icefall"},{"title":"briansidp/whisperbiasing","url":"https://github.com/briansidp/whisperbiasing"},{"title":"audioshake/alt-eval","url":"https://github.com/audioshake/alt-eval"},{"title":"robflynnyh/long-context-asr","url":"https://github.com/robflynnyh/long-context-asr"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/1/whisper"},{"title":"open-creator/icefall","url":"https://github.com/open-creator/icefall"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-portuguese","task":"Speech Recognition","dataset_variant":"Common Voice Portuguese","rows":1,"metrics":["Test WER"],"first_row_in_archive_order":{"model":"XLSR53 Wav2Vec2 Portuguese by Orlem Santos","paper":"/paper/xlsr53-wav2vec2-portuguese-by-orlem-santos","metrics":{"Test WER":"10.74%"},"code_links":[{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/5/wav2vec2_with_lm"},{"title":"Orlllem/wav2vec2-fairseq-pt-br","url":"https://github.com/Orlllem/wav2vec2-fairseq-pt-br"},{"title":"MindCode-4/code-10","url":"https://github.com/MindCode-4/code-10/tree/main/AECRNet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-russian","task":"Speech Recognition","dataset_variant":"Common Voice Russian","rows":1,"metrics":["Test WER","Test CER","Test CER (+LM)","Test WER (+LM)"],"first_row_in_archive_order":{"model":"Whisper (Large v2)","paper":"/paper/robust-speech-recognition-via-large-scale-1","metrics":{"Test WER":"7.1%"},"code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"openai/whisper","url":"https://github.com/openai/whisper"},{"title":"ggerganov/whisper.cpp","url":"https://github.com/ggerganov/whisper.cpp"},{"title":"m-bain/whisperx","url":"https://github.com/m-bain/whisperx"},{"title":"sanchit-gandhi/whisper-jax","url":"https://github.com/sanchit-gandhi/whisper-jax"},{"title":"whisperspeech/whisperspeech","url":"https://github.com/whisperspeech/whisperspeech"},{"title":"collabora/whisperspeech","url":"https://github.com/collabora/whisperspeech"},{"title":"collabora/whisperlive","url":"https://github.com/collabora/whisperlive"},{"title":"kadirnar/whisper-plus","url":"https://github.com/kadirnar/whisper-plus"},{"title":"k2-fsa/icefall","url":"https://github.com/k2-fsa/icefall"},{"title":"briansidp/whisperbiasing","url":"https://github.com/briansidp/whisperbiasing"},{"title":"audioshake/alt-eval","url":"https://github.com/audioshake/alt-eval"},{"title":"robflynnyh/long-context-asr","url":"https://github.com/robflynnyh/long-context-asr"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/1/whisper"},{"title":"open-creator/icefall","url":"https://github.com/open-creator/icefall"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/audio-classification-on-common-voice-16-1","task":"Audio Classification","dataset_variant":"Common Voice 16.1","rows":0,"metrics":["Test Accent Accuracy","Test Age Accuracy"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice","task":"Speech Recognition","dataset_variant":"Common Voice Interlingua","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-1","task":"Speech Recognition","dataset_variant":"Common Voice Kinyarwanda","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-1-0-french","task":"Speech Recognition","dataset_variant":"Common Voice 1.0 French","rows":0,"metrics":["Wer"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-7-0","task":"Speech Recognition","dataset_variant":"Common Voice 7.0 Swedish","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-7-0-1","task":"Speech Recognition","dataset_variant":"Common Voice 7.0 Bashkir","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-7-0-13","task":"Speech Recognition","dataset_variant":"Common Voice 7.0 Italian","rows":0,"metrics":["Test CER","Test CER (+LM)","Test WER","Test WER (+LM)"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-7-0-2","task":"Speech Recognition","dataset_variant":"Common Voice 7.0 Assamese","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-7-0-23","task":"Speech Recognition","dataset_variant":"Common Voice 7.0 Turkish","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-7-0-25","task":"Speech Recognition","dataset_variant":"Common Voice 7.0 Punjabi","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-7-0-27","task":"Speech Recognition","dataset_variant":"Common Voice 7.0 Japanese","rows":0,"metrics":["Test CER (with LM)","Test WER (with LM)"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-7-0-29","task":"Speech Recognition","dataset_variant":"Common Voice 7.0 Portuguese","rows":0,"metrics":["Test WER on Common Voice 7"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-7-0-32","task":"Speech Recognition","dataset_variant":"Common Voice 7.0 Luganda","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-7-0-4","task":"Speech Recognition","dataset_variant":"Common Voice 7.0 Vietnamese","rows":0,"metrics":["Test CER (with LM)","Test WER","Test WER (with LM)","Test WER (with Language model)"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-7-0-5","task":"Speech Recognition","dataset_variant":"Common Voice 7.0 Finnish","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-7-0-abkhaz","task":"Speech Recognition","dataset_variant":"Common Voice 7.0 Abkhaz","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-7-0-arabic","task":"Speech Recognition","dataset_variant":"Common Voice 7.0 Arabic","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-7-0-basque","task":"Speech Recognition","dataset_variant":"Common Voice 7.0 Basque","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-7-0-french","task":"Speech Recognition","dataset_variant":"Common Voice 7.0 French","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-7-0-german","task":"Speech Recognition","dataset_variant":"Common Voice 7.0 German","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-7-0-hindi","task":"Speech Recognition","dataset_variant":"Common Voice 7.0 Hindi","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-7-0-odia","task":"Speech Recognition","dataset_variant":"Common Voice 7.0 Odia","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-7-0-thai","task":"Speech Recognition","dataset_variant":"Common Voice 7.0 Thai","rows":0,"metrics":["Test CER","Test SER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-7-0-votic","task":"Speech Recognition","dataset_variant":"Common Voice 7.0 Votic","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Swedish","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-1","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Kurmanji Kurdish","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-10","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Bulgarian","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-11","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Marathi","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-12","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Latvian","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-13","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Georgian","rows":0,"metrics":["CER LM","WER LM"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-15","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Indonesian","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-16","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Spanish","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-19","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Estonian","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-2","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Punjabi","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-20","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Portuguese","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-21","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Ukrainian","rows":0,"metrics":["CER LM","WER LM"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-22","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Maltese","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-23","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Romanian","rows":0,"metrics":["Test CER (with LM)","Test CER (without LM)","Test WER (with LM)","Test WER (without LM)"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-24","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Slovenian","rows":0,"metrics":["Test CER","Test CER (+LM)","Test WER","Test WER (+LM)"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-26","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Mongolian","rows":0,"metrics":["Test CER using LM","Test WER using LM"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-29","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Assamese","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-3","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Central Kurdish","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-30","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Sorbian, Upper","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-31","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Interlingua","rows":0,"metrics":["Test CER using LM","Test WER using LM"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-32","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Romansh Sursilvan","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-33","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Romansh Vallader","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-35","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Vietnamese","rows":0,"metrics":["Test CER (with LM)","Test WER","Test WER (with LM)"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-37","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Russian","rows":0,"metrics":["Test CER","Test CER (+LM)","Test WER","Test WER (+LM)"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-38","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Santali (Ol Chiki)","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-39","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Serbian","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-4","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Catalan","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-40","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Guarani","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-41","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Galician","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-6","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Armenian","rows":0,"metrics":["CER LM","WER LM"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-7","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Swahili","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-8","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Hungarian","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-9","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Japanese","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-abkhaz","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Abkhaz","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-arabic","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Arabic","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-basaa","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Basaa","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-breton","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Breton","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-czech","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Czech","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-dutch","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Dutch","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-erzya","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Erzya","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-french","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 French","rows":0,"metrics":["Test CER","Test CER (with LM)","Test WER","Test WER (with LM)"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-german","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 German","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-greek","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Greek","rows":0,"metrics":["Test CER using LM","Test WER using LM"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-hausa","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Hausa","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-hindi","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Hindi","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-kabyle","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Kabyle","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-kazakh","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Kazakh","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-odia","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Odia","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-polish","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Polish","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-sakha","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Sakha","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-slovak","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Slovak","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-tatar","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Tatar","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-urdu","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Urdu","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-uyghur","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Uyghur","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-uzbek","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Uzbek","rows":0,"metrics":["Test CER (no LM)","Test CER (with LM)","Test WER (no LM)","Test WER (with LM)"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-8-0-votic","task":"Speech Recognition","dataset_variant":"Common Voice 8.0 Votic","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-arabic","task":"Speech Recognition","dataset_variant":"Common Voice Arabic","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-assamese","task":"Speech Recognition","dataset_variant":"Common Voice Assamese","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-basque","task":"Speech Recognition","dataset_variant":"Common Voice Basque","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-breton","task":"Speech Recognition","dataset_variant":"Common Voice Breton","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-catalan","task":"Speech Recognition","dataset_variant":"Common Voice Catalan","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-chinese","task":"Speech Recognition","dataset_variant":"Common Voice Chinese (Hong Kong)","rows":0,"metrics":["Test CER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-chinese-2","task":"Speech Recognition","dataset_variant":"Common Voice Chinese (China)","rows":0,"metrics":["Test CER","Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-chuvash","task":"Speech Recognition","dataset_variant":"Common Voice Chuvash","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-czech","task":"Speech Recognition","dataset_variant":"Common Voice Czech","rows":0,"metrics":["Test WER","Test CER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-dhivehi","task":"Speech Recognition","dataset_variant":"Common Voice Dhivehi","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-dutch","task":"Speech Recognition","dataset_variant":"Common Voice Dutch","rows":0,"metrics":["Test WER","Test CER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-esperanto","task":"Speech Recognition","dataset_variant":"Common Voice Esperanto","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-estonian","task":"Speech Recognition","dataset_variant":"Common Voice Estonian","rows":0,"metrics":["Test WER","Test CER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-finnish","task":"Speech Recognition","dataset_variant":"Common Voice Finnish","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-galician","task":"Speech Recognition","dataset_variant":"Common Voice Galician","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-georgian","task":"Speech Recognition","dataset_variant":"Common Voice Georgian","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-greek","task":"Speech Recognition","dataset_variant":"Common Voice Greek","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-hakha-chin","task":"Speech Recognition","dataset_variant":"Common Voice Hakha Chin","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-hindi","task":"Speech Recognition","dataset_variant":"Common Voice Hindi","rows":0,"metrics":["Test WER","Test CER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-hungarian","task":"Speech Recognition","dataset_variant":"Common Voice Hungarian","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-indonesian","task":"Speech Recognition","dataset_variant":"Common Voice Indonesian","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-irish","task":"Speech Recognition","dataset_variant":"Common Voice Irish","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-kyrgyz","task":"Speech Recognition","dataset_variant":"Common Voice Kyrgyz","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-latvian","task":"Speech Recognition","dataset_variant":"Common Voice Latvian","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-lithuanian","task":"Speech Recognition","dataset_variant":"Common Voice Lithuanian","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-luganda","task":"Speech Recognition","dataset_variant":"Common Voice Luganda","rows":0,"metrics":["Test WER","Test CER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-maltese","task":"Speech Recognition","dataset_variant":"Common Voice Maltese","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-mongolian","task":"Speech Recognition","dataset_variant":"Common Voice Mongolian","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-odia","task":"Speech Recognition","dataset_variant":"Common Voice Odia","rows":0,"metrics":["Test WER","Test CER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-persian","task":"Speech Recognition","dataset_variant":"Common Voice Persian","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-polish","task":"Speech Recognition","dataset_variant":"Common Voice Polish","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-punjabi","task":"Speech Recognition","dataset_variant":"Common Voice Punjabi","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-romanian","task":"Speech Recognition","dataset_variant":"Common Voice Romanian","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-romansh","task":"Speech Recognition","dataset_variant":"Common Voice Romansh Vallader","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-romansh-1","task":"Speech Recognition","dataset_variant":"Common Voice Romansh Sursilvan","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-sakha","task":"Speech Recognition","dataset_variant":"Common Voice Sakha","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-slovenian","task":"Speech Recognition","dataset_variant":"Common Voice Slovenian","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-sorbian","task":"Speech Recognition","dataset_variant":"Common Voice Sorbian, Upper","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-swedish","task":"Speech Recognition","dataset_variant":"Common Voice Swedish","rows":0,"metrics":["Test WER","Test CER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-tamil","task":"Speech Recognition","dataset_variant":"Common Voice Tamil","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-tatar","task":"Speech Recognition","dataset_variant":"Common Voice Tatar","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-thai","task":"Speech Recognition","dataset_variant":"Common Voice Thai","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-turkish","task":"Speech Recognition","dataset_variant":"Common Voice Turkish","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-ukrainian","task":"Speech Recognition","dataset_variant":"Common Voice Ukrainian","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-vietnamese","task":"Speech Recognition","dataset_variant":"Common Voice Vietnamese","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-common-voice-welsh","task":"Speech Recognition","dataset_variant":"Common Voice Welsh","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-mozilla-common-voice-10","task":"Speech Recognition","dataset_variant":"Mozilla Common Voice 10.0","rows":0,"metrics":["Dev WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-mozilla-common-voice-16","task":"Speech Recognition","dataset_variant":"Mozilla Common Voice 16.1","rows":0,"metrics":["Test WER (De)","Test WER (ES)","Test WER (En)","Test WER (Fr)"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-mozilla-common-voice-7","task":"Speech Recognition","dataset_variant":"Mozilla Common Voice 7.0","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-mozilla-common-voice-8","task":"Speech Recognition","dataset_variant":"Mozilla Common Voice 8.0","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-mozilla-common-voice-9","task":"Speech Recognition","dataset_variant":"Mozilla Common Voice 9.0","rows":0,"metrics":["Test WER"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/mt-slvr-multi-task-self-supervised-learning","title":"MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In(Variant) Representations","date":"2023-05-29","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/fast-conformer-with-linearly-scalable","title":"Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition","date":"2023-05-08","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/improving-the-previous-state-of-the-art","title":"Improving the previous state-of-the-art Frisian ASR by fine-tuning XLS-R","date":"2023-03-31","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/robust-speech-recognition-via-large-scale-1","title":"Robust Speech Recognition via Large-Scale Weak Supervision","date":"2022-12-06","rows_on_this_dataset":7,"code_links":15,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":59,"samples_ran":5,"samples_unverified":54,"pointer_only_for_licence":18,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/automatic-speech-recognition-in-german-a","title":"Automatic Speech Recognition in German: A Detailed Error Analysis","date":"2022-08-03","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/tevr-improving-speech-recognition-by-token","title":"TEVR: Improving Speech Recognition by Token Entropy Variance Reduction","date":"2022-06-25","rows_on_this_dataset":5,"code_links":2,"syntology":null},{"paper":"/paper/wav2vec2-base-vietnamese-160h","title":"Wav2vec2 Base Vietnamese 160h","date":"2022-05-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/xlsr53-wav2vec2-portuguese-by-orlem-santos","title":"XLSR53 Wav2Vec2 Portuguese by Orlem Santos","date":"2022-02-01","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/scribosermo-fast-speech-to-text-models-for","title":"Scribosermo: Fast Speech-to-Text models for German and other Languages","date":"2021-10-15","rows_on_this_dataset":13,"code_links":3,"syntology":null},{"paper":"/paper/bigssl-exploring-the-frontier-of-large-scale","title":"BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition","date":"2021-09-27","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/vietnamese-end-to-end-speech-recognition","title":"Vietnamese end-to-end speech recognition using wav2vec 2.0","date":"2021-09-02","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/speechstew-simply-mix-all-available-speech","title":"SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network","date":"2021-04-05","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/voxpopuli-a-large-scale-multilingual-speech","title":"VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation","date":"2021-01-02","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/nemo-a-toolkit-for-building-ai-applications","title":"NeMo: a toolkit for building AI applications using Neural Modules","date":"2019-09-14","rows_on_this_dataset":6,"code_links":1,"syntology":null},{"paper":"/paper/chunkformer-masked-chunking-conformer-for-1","title":"ChunkFormer: Masked Chunking Conformer For Long-Form Speech Transcription","date":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":60,"samples_ran":6,"samples_unverified":54,"pointer_only_for_licence":19,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}