{
"_id": "621ffdc136468d709f17ae45",
"id": "facebook/wav2vec2-base-960h",
"modelId": "facebook/wav2vec2-base-960h",
"author": "facebook",
"sha": "22aad52d435eb6dbaf354bdad9b0da84ce7d6156",
"lastModified": "2022-11-14T21:37:23.000Z",
"private": false,
"disabled": false,
"gated": false,
"pipeline_tag": "automatic-speech-recognition",
"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",
"endpoints_compatible",
"has_space",
"region:us"
],
"downloads": 1067025,
"library_name": "transformers",
"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"
}
],
"likes": 172,
"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"
},
"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"
},
"spaces": [
"AIGC-Audio/AudioGPT",
"radames/edit-video-by-editing-text",
"rajistics/Financial_Analyst_AI",
"Gradio-Blocks/Create_GIFs_from_Video",
"awacke1/TTS-STT-Blocks",
"reach-vb/asr-pyctcdecode",
"Kameswara/TextToVideo",
"Gradio-Blocks/SlowMo_n_Timelapse_Your_Video",
"awacke1/ASRGenerateStoryandVideo",
"awacke1/ASRGenerateStory",
"siddh4rth/audio_to_text",
"r2d2/speech2text",
"priyanshu02/Linguistics-Accents",
"DrishtiSharma/ASR_using_Wav2Vec2",
"abidlabs/crowd-speech",
"Gradio-Blocks/CloudSaveText2Speech",
"rajistics/Ask-Wiki",
"rsatish1110/AudioToTextToStoryToImageToVideo",
"HighCWu/anime-colorization-with-hint",
"Laronix/Laronix_ASR_TTS_VC",
"Sakil/english_audio_transcriptor",
"epdavid2/morsecode",
"awacke1/ASRtoTexttoStorytoImagestoVideo",
"freddyaboulton/all_demos_3",
"datnth1709/FantasticFour-S2T-MT-demo",
"knkarthick/Meeting-Demo",
"AIZerotoHero-Health4All/01-Gradio-Speech2Text2Speech-AIPipeline",
"alecmueller/01-Speech2Text2Speech-GR",
"knkarthick/Meeting-Use-Cases",
"ericsali/language_translator",
"Deepsheka/newdemo-app",
"GroveStreet/GTA_SOVITS",
"piecurus/speech_to_text",
"ThirdIringan/Speech_Equation_Solver",
"awacke1/Text2SpeechSentimentSave",
"awacke1/NLPAutoAI",
"awacke1/SpeechStoryReadAloud",
"uparasha/ASRtoTexttoStorytoImagestoVideo",
"akashagarwal/ASRGenerateStory",
"awacke1/Speeech2Text2Story2Images2Video",
"rajatus231/Speeech2Text2Story2Images2Video",
"MateusA/StoryGenerator",
"ocordes/GradioSpeechToTextToMedia",
"awacke1/GradioSpeech2Text2Story2Images2Video",
"mm2593/Gradiospeech2Text2Story2Video",
"manjuvallayil/te-reo",
"sandeepmajumdar/nlp-sorcery",
"freddyaboulton/3.1.4.9-all-demos",
"salashvijay/audiototxttosentiment",
"RachAmm/Wav2vec-vs-Whisper",
"TheFriendlyNPC/French_Translation_Audio",
"bharathraj-v/audio-content-analysis",
"Rongjiehuang/GenerSpeech",
"AIZerotoHero-Health4All/01-Speech2Text2Speech",
"rrichaz/TTS-STT-Blocks",
"yash-srivastava19/TRINIT_EzDub_ML01",
"awacke1/GradioVoicetoTexttoSentiment",
"RealTimeLiveAIForHealth/VoicetoTexttoSentiment",
"awacke1/SpeechRecognitionwithWav2Vec2",
"mushroomsolutions/Gallery",
"bookbot/SpeechLine",
"UndueTarget/audioFILE_to_text",
"predictive-singularity/Singularity",
"raghuram13/Audiototext",
"on1onmangoes/mango1",
"yl12053/so-vits-4.1-Grass-Wonder",
"yl12053/so-vits-4.1-Kitasan-Black",
"ahdsoft/Persian-Automatic-Speech-Recognition",
"yl12053/so-vits-4.1-Matikanefukukitaru",
"aupfe08/stt_or_tts",
"eetn/hellenic_demo_omar",
"eetn/hellenic_demo_maria",
"eetn/g",
"Vasiliki/demo",
"eetn/hellenic_demo_mediabilly",
"course-demos/blocks_multi_step",
"ysharma/Slowmo-timelapse-Video-with-ASR",
"awacke1/STT-TTS-ASR-AI-NLP-Pipeline",
"Aurelle/ASR-with-Wave2vec2",
"InesGahlouzi/speech_recog",
"atomiclabs/ASR",
"santoshsindham/ASRGenerateStory",
"PrafulUHG/ASRGenerateStory",
"palak23/ASRGenerateStory",
"jaydeepkum/ASRtoTexttoStorytoImagestoVideo",
"sthammis/ASR2Text2Video",
"gpai2/ASRtoTexttoStorytoImagetoVideo",
"Chethan003/asrtotexttostorytoimagestovideo",
"ayush312/ASRtext_to_image",
"Zaharul/ASRtexttostory",
"niksyad/SpeechToTextToStoryToImagesToVideo",
"Vasanthp/ASRGenerateStory",
"peekaboo/GenerateStory",
"MadhuV28/gradioSPeechToTextToImagesTOVideo",
"vsaripella/GradioSpeech2Text2Story2Images2Video",
"vnemala/ASRGenerateStory",
"AkB/meta-ASR",
"rashid101b/Asr-Wav2Vec2",
"Priyabrata017/ASRtoTexttoStorytoImagestoVideos",
"freddyaboulton/all_demos",
"freddyaboulton/all_demos_2",
"freddyaboulton/9-all-demos",
"SamSwift/Home_Automation",
"Arwin/Asr_with_wav2vec2",
"PraveenBhargav/SpeechRecognition_Wav2Vec2",
"johngoad/automatic-speech-recognition",
"VMORnD/ASS",
"minhnd/speech-recognize",
"TheFriendlyNPC/Spanish_translation_audio",
"vonewman/ASR-in-English",
"krishnasai99/NLP",
"jhescheles/01_speech_to_text_to_speech",
"tritter2/01-Speech2Text2Speech",
"goetzjj/Speech2Text2Speech_class",
"jharms10/01-Speech2Text2Speech",
"dabram2/AIClassspeechTextSpeech",
"Paulz/Wav2Vec2_ASR_1",
"su12/ASR",
"Naram/asr-wav2vec2",
"Irshad/ASR-with-Wave2Vec2",
"Paulz/ASR",
"sonobit/airesearch-TH",
"KevinGeng/Laronix_PAL_ASR_Offline_Plot",
"bharathraj-v/call-recording-analysis",
"Fibi31/MYSPACE",
"tanub/ASR-with-WAV2VEC2",
"jbraun19/GradioVoicetoTexttoSentiment",
"abidlabs/tabs-api",
"LaraRamos/ASR-with-Wav2Vec2.0",
"Sindhura83/project",
"Harshitha-534/STT",
"abdualimov/Universal_Video_Translator",
"awacke1/ASR-facebook-wav2vec2-base-960h",
"DemoLou/text-to-speech-test",
"abidlabs/stt_or_tts",
"Chakshu123/sketch-colorization-with-hint",
"priyanshu02/minorProj",
"jumei/gptsite",
"sunxianfeng/gptsite",
"wagewg/gpt",
"hlby/gpt",
"feifeifeiliu/TalkSHOW",
"andresad/Wav2Vec-orders-spanish",
"AsadullaX/TestCHatBot",
"funnypaper/TalkGPT",
"ericsali/trans",
"siddhikasriram/facebook-wav2vec2-base-960h",
"Manto2023/AudioGPT",
"Datasculptor/AudioGPT",
"Irahgem/ASR-Wav2vec",
"Irahgem/Speech_Lab_Wav2Vec2",
"z11h/AudioGPT",
"prachibindal/VoiceToText",
"alonegg/AudioGPT",
"knkn01/speech_recognition_cnn",
"Chakshu123/image-colorization-with-hint",
"Has-ai/Audio-Audio",
"Ld75/pyannote-speaker-diarization",
"GreenRaptor/Interview-GPT",
"Satinurus/AudioGPT",
"Jabrain/Zbot",
"spycoder/wav2vec",
"satyawrat/ASR-using-wav2vec",
"adarsh8986/facebook-wav2vec2-base-960h",
"techysanoj/avishkaar-check",
"darksakura/l1",
"Yusen/So-VITS-4.1",
"vickyji/trying",
"aditii09/whisper_asr_english",
"jingwora/voice-speech-sentiment",
"totoshi/test",
"issacneedsbread/audio-to-text-simplistic",
"issacneedsbread/audio2text",
"HakimHa/wanderJoy",
"yl12053/so-vits-4.1-Special-Week",
"yl12053/so-vits-4.1-Mejiro-Mcqueen",
"yl12053/so-vits-4.1-Manhattan-Cafe",
"yl12053/so-vits-4.1-Slience-Suzuka",
"yl12053/so-vits-4.1-Rice-Shower",
"yl12053/so-vits-4.1-Tokai-Teio",
"yl12053/so-vits-4.1-Seiun-Sky",
"suanlixianren/sovits_test",
"suanlixianren/sovits_test2",
"tripnine/facebook-wav2vec2-base-960h",
"Nultx/speech2text",
"yl12053/so-vits-4.1-Mihono-Bourbon",
"srima/speech_to_text",
"yl12053/so-vits-4.1-Curren-Chan",
"yl12053/so-vits-4.1-Gold-Ship",
"yl12053/so-vits-4.1-Satono-Diamond",
"yl12053/so-vits-4.1-Special-Week-Remake",
"adityasrathore/Financial_Analyst_AI",
"yl12053/so-vits-4.1-Daiwa-Scarlet",
"yaoqi/blocks-multi-step",
"jaumaras/gradioTest1",
"jaumaras/AudioAppSpace",
"josemercado/Sistema_RAH",
"pechb/facebook-wav2vec2-base-960h",
"yl12053/so-vits-4.1-Matikanetannhauser",
"yl12053/so-vits-4.1-Mejiro-Ardan",
"yl12053/so-vits-4.1-Nice-Nature",
"aupfe08/blocks_speech_text_sentiment",
"lampongyuen/Gradio-Transcribe",
"wasertech/open_asr_leaderboard",
"issacneedsbread/Digital-gramophone-Mk1",
"issacneedsbread/Digital-record-player",
"K00B404/AudioAppSpace_custom",
"mozgov/so-vits-4.1-Matikanefukukitaru",
"liyaodev/so-vits-4.1-Matikanefukukitaru",
"liyaodev/so-vits-svc-shengshuyan",
"mozgov/so-vits-svc-shengshuyan",
"HugDev/MyASR",
"NamAnh/speech2tex",
"truongghieu/facebook-wav2vec2-base-960h",
"kaljuvee/Financial_Analyst_AI",
"aliabd/testing-fork-prs",
"kushan1988/VITS-TEST",
"Shanuka01/VITS-TEST_02",
"neuralleap/SO-VITS_Test",
"aoxiang1221/so-vits-svc",
"SSHAMZZ/Host_trial_1",
"dinssync/tts",
"ayaushbhetuwal/facebook-wav2vec2-base-960h",
"KevinGeng/Laronix_Recording",
"meghana16/sttgradio",
"steedmonteiro/VoicetoTexttoSentiment",
"tasks-ai/speech-to-text",
"Skier8402/ASR_demo",
"shivam0126/Speech_recongination_using_word2vec2",
"NgocHieu/ASR-with-Wav2Vec",
"hankzero00001/edit-video-by-editing-text",
"anishkadve/Speech-Recognition-Using-Deep-Learning",
"lampongyuen/Gradio-Transcribe-Translate",
"Hentinel/test-stt-1",
"Severian/speech-to-text",
"GroveStreet/GTAVC_SOVITS",
"JavierGon12/retrAIced"
],
"safetensors": {
"parameters": {
"F32": 94395552
},
"total": 94395552
},
"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"
}
],
"createdAt": "2022-03-02T23:29:05.000Z"
}