{"_id":"621ffdc136468d709f17ae45","id":"facebook/wav2vec2-base-960h","private":false,"pipeline_tag":"automatic-speech-recognition","library_name":"transformers","tags":["transformers","pytorch","tf","safetensors","wav2vec2","automatic-speech-recognition","audio","hf-asr-leaderboard","en","dataset:librispeech_asr","arxiv:2006.11477","license:apache-2.0","model-index","eval-results","endpoints_compatible","deploy:azure","region:us"],"downloads":1318393,"likes":402,"modelId":"facebook/wav2vec2-base-960h","author":"facebook","sha":"22aad52d435eb6dbaf354bdad9b0da84ce7d6156","lastModified":"2022-11-14T21:37:23.000Z","gated":false,"disabled":false,"widgetData":[{"example_title":"Librispeech sample 1","src":"https://cdn-media.huggingface.co/speech_samples/sample1.flac"},{"example_title":"Librispeech sample 2","src":"https://cdn-media.huggingface.co/speech_samples/sample2.flac"}],"model-index":[{"name":"wav2vec2-base-960h","results":[{"task":{"name":"Automatic Speech Recognition","type":"automatic-speech-recognition"},"dataset":{"name":"LibriSpeech (clean)","type":"librispeech_asr","config":"clean","split":"test","args":{"language":"en"}},"metrics":[{"name":"Test WER","type":"wer","value":3.4,"verified":false}]},{"task":{"name":"Automatic Speech Recognition","type":"automatic-speech-recognition"},"dataset":{"name":"LibriSpeech (other)","type":"librispeech_asr","config":"other","split":"test","args":{"language":"en"}},"metrics":[{"name":"Test WER","type":"wer","value":8.6,"verified":false}]}]}],"config":{"architectures":["Wav2Vec2ForCTC"],"model_type":"wav2vec2","tokenizer_config":{"unk_token":"<unk>","bos_token":"<s>","eos_token":"</s>","pad_token":"<pad>"}},"cardData":{"language":"en","datasets":["librispeech_asr"],"tags":["audio","automatic-speech-recognition","hf-asr-leaderboard"],"license":"apache-2.0","widget":[{"example_title":"Librispeech sample 1","src":"https://cdn-media.huggingface.co/speech_samples/sample1.flac"},{"example_title":"Librispeech sample 2","src":"https://cdn-media.huggingface.co/speech_samples/sample2.flac"}],"model-index":[{"name":"wav2vec2-base-960h","results":[{"task":{"name":"Automatic Speech Recognition","type":"automatic-speech-recognition"},"dataset":{"name":"LibriSpeech (clean)","type":"librispeech_asr","config":"clean","split":"test","args":{"language":"en"}},"metrics":[{"name":"Test WER","type":"wer","value":3.4,"verified":false}]},{"task":{"name":"Automatic Speech Recognition","type":"automatic-speech-recognition"},"dataset":{"name":"LibriSpeech (other)","type":"librispeech_asr","config":"other","split":"test","args":{"language":"en"}},"metrics":[{"name":"Test WER","type":"wer","value":8.6,"verified":false}]}]}]},"transformersInfo":{"auto_model":"AutoModelForCTC","pipeline_tag":"automatic-speech-recognition","processor":"AutoProcessor"},"siblings":[{"rfilename":".gitattributes"},{"rfilename":"README.md"},{"rfilename":"config.json"},{"rfilename":"feature_extractor_config.json"},{"rfilename":"model.safetensors"},{"rfilename":"preprocessor_config.json"},{"rfilename":"pytorch_model.bin"},{"rfilename":"special_tokens_map.json"},{"rfilename":"tf_model.h5"},{"rfilename":"tokenizer_config.json"},{"rfilename":"vocab.json"}],"spaces":["mteb/leaderboard","hf-audio/open_asr_leaderboard","andrasnest/wan-loop-generator","alexnasa/Wan2.2-Animate-ZEROGPU","alexnasa/OmniAvatar","Uthar/SexyReality","microsoft/paza-bench","eduagarcia/multilingual-tokenizer-leaderboard","kulkas2pintu/Video_to_video_WAN","kulkas2pintu/Video_to_video_WAN2","gunship999/SexyImages","H-Liu1997/TANGO","Yntec/ToyWorld","AIGC-Audio/AudioGPT","radames/edit-video-by-editing-text","anycoderapps/Z-Image-Turbo","Skywork/skyreels-a1-talking-head","llamameta/flux-pro-uncensored","acvlab/FantasyTalking","Yntec/PrintingPress","Nymbo/Compare-6","rajistics/Financial_Analyst_AI","C4G-HKUST/AnyTalker","llamameta/fluxproV2","fffiloni/MEMO","Yntec/ToyWorldXL","Yntec/blitz_diffusion","John6666/Diffusion80XX4sg","jbilcke-hf/OmniAvatar","Gradio-Blocks/Create_GIFs_from_Video","John6666/PrintingPress4","llamameta/fast-sd3.5-large","Soul-AILab/SoulX-FlashHead","Yntec/Image-Models-Test-2024","Yntec/Image-Models-Test-April-2024","DemiPoto/TestDifs","Abinivesh/Multi-models-prompt-to-image-generation","NativeAngels/Compare-6","herokominato/Wan2.2-Animate-ZEROGPU","reach-vb/asr-pyctcdecode","John6666/hfd_test_nostopbutton","Kameswara/TextToVideo","Nymbo/Diffusion80XX4sg","DemiPoto/testSortModels","kaleidoskop-hug/PrintingPress","artificialguybr/EchoMimicV3-Demo","hugging-apps/leaptalk-talking-head","Gradio-Blocks/SlowMo_n_Timelapse_Your_Video","awacke1/ASRGenerateStoryandVideo","awacke1/ASRGenerateStory","Chakshu123/image-colorization-with-hint","abdualimov/Universal_Video_Translator","GroveStreet/GTA_SOVITS","Yntec/MiniToyWorld","siddh4rth/audio_to_text","yl12053/so-vits-4.1-Tokai-Teio","John6666/ToyWorld4","Steveeeeeeen/ASR-comparaison","svjack/FantasyTalking","JavierGon12/retrAIced","John6666/Diffusion80XX4g","SAITAN666/StableDiffusion35Large-Image-Models-Test-November-2024","NativeAngels/HuggingfaceDiffusion","NativeAngels/ToyWorld","Yntec/Image-Models-Test-December-2024","prathameshv07/Multilingual-Audio-Intelligence-System","build-small-hackathon/Rizz-Therapy","r2d2/speech2text","priyanshu02/Linguistics-Accents","yl12053/so-vits-4.1-Special-Week","neuroama/so-vits-svc","peechapp/PeechTTSv22050","John6666/Diffusion80XX4","K00B404/HuggingfaceDiffusion_custom","John6666/blitz_diffusion4","John6666/blitz_diffusion_builtin","K00B404/SimpleBrothel","Gradio-Blocks/CloudSaveText2Speech","rsatish1110/AudioToTextToStoryToImageToVideo","rajistics/Ask-Wiki","HighCWu/anime-colorization-with-hint","ericsali/language_translator","feifeifeiliu/TalkSHOW","yl12053/so-vits-4.1-Rice-Shower","GroveStreet/GTAVC_SOVITS","yl12053/so-vits-4.1-Matikanetannhauser","yl12053/so-vits-4.1-Matikanefukukitaru","KasugaiSakura/so-vits-svc-Sora","Nymbo/edit-video-by-editing-text","Blane187/multi-diffusion","bpiyush/SoundOfWater","Uthar/LewdExperiments","Uthar/BodyPaint","Uthar/HRGiger","Uthar/HighFashion","KuyaToto/wav2vec2-api","Oluko/yoruba-practice","Sakil/english_audio_transcriptor","awacke1/ASRtoTexttoStorytoImagestoVideo","abidlabs/crowd-speech"],"createdAt":"2022-03-02T23:29:05.000Z","safetensors":{"parameters":{"F32":94395552},"total":94395552},"usedStorage":2503111080}