← Back to index
facebook/wav2vec2-base-960h
Inference API (serverless) is disabled for an unknown reason. Please open a Discussion in the Community tab.
			{
  "_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",
    "region:us"
  ],
  "downloads": 1231777,
  "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": 306,
  "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": [
    "AIGC-Audio/AudioGPT",
    "radames/edit-video-by-editing-text",
    "Yntec/ToyWorld",
    "Yntec/HuggingfaceDiffusion",
    "Yntec/PrintingPress",
    "Nymbo/Compare-6",
    "llamameta/flux-pro-uncensored",
    "rajistics/Financial_Analyst_AI",
    "Yntec/ToyWorldXL",
    "llamameta/fluxproV2",
    "Yntec/blitz_diffusion",
    "phenixrhyder/NSFW-ToyWorld",
    "Gradio-Blocks/Create_GIFs_from_Video",
    "John6666/Diffusion80XX4sg",
    "reach-vb/asr-pyctcdecode",
    "Kameswara/TextToVideo",
    "DemiPoto/TestDifs",
    "John6666/PrintingPress4",
    "Gradio-Blocks/SlowMo_n_Timelapse_Your_Video",
    "awacke1/ASRGenerateStoryandVideo",
    "DemiPoto/testSortModels",
    "Yntec/october-2024-image-models",
    "awacke1/ASRGenerateStory",
    "siddh4rth/audio_to_text",
    "Yntec/MiniPrintingPress",
    "Yntec/StableDiffusion35Large-Image-Models-Test-November-2024",
    "Chakshu123/sketch-colorization-with-hint",
    "abdualimov/Universal_Video_Translator",
    "JavierGon12/retrAIced",
    "Steveeeeeeen/ASR-comparaison",
    "Nymbo/Diffusion80XX4sg",
    "John6666/hfd_test_nostopbutton",
    "llamameta/fast-sd3.5-large",
    "r2d2/speech2text",
    "Chakshu123/image-colorization-with-hint",
    "priyanshu02/Linguistics-Accents",
    "yl12053/so-vits-4.1-Tokai-Teio",
    "GroveStreet/GTA_SOVITS",
    "yl12053/so-vits-4.1-Special-Week",
    "neuroama/so-vits-svc",
    "John6666/ToyWorld4",
    "John6666/Diffusion80XX4g",
    "K00B404/HuggingfaceDiffusion_custom",
    "abidlabs/crowd-speech",
    "Gradio-Blocks/CloudSaveText2Speech",
    "rsatish1110/AudioToTextToStoryToImageToVideo",
    "rajistics/Ask-Wiki",
    "HighCWu/anime-colorization-with-hint",
    "feifeifeiliu/TalkSHOW",
    "yl12053/so-vits-4.1-Rice-Shower",
    "yl12053/so-vits-4.1-Matikanetannhauser",
    "yl12053/so-vits-4.1-Matikanefukukitaru",
    "KasugaiSakura/so-vits-svc-Sora",
    "peechapp/PeechTTSv22050",
    "John6666/Diffusion80XX4",
    "John6666/blitz_diffusion4",
    "Sakil/english_audio_transcriptor",
    "awacke1/ASRtoTexttoStorytoImagestoVideo",
    "freddyaboulton/all_demos_3",
    "epdavid2/morsecode",
    "datnth1709/FantasticFour-S2T-MT-demo",
    "knkarthick/Meeting-Demo",
    "knkarthick/Meeting-Use-Cases",
    "AIZerotoHero-Health4All/01-Gradio-Speech2Text2Speech-AIPipeline",
    "alecmueller/01-Speech2Text2Speech-GR",
    "ericsali/language_translator",
    "Deepsheka/newdemo-app",
    "Yusen/So-VITS-4.1",
    "GroveStreet/GTAVC_SOVITS",
    "yl12053/so-vits-4.1-Kitasan-Black",
    "yl12053/so-vits-4.1-Daiwa-Scarlet",
    "wasertech/open_asr_leaderboard",
    "aoxiang1221/so-vits-svc",
    "Nymbo/edit-video-by-editing-text",
    "Blane187/multi-diffusion",
    "Yntec/MiniToyWorld",
    "Yntec/MiniHuggingfaceDiffusion",
    "None1145/So-VITS-SVC",
    "SAITAN666/StableDiffusion35Large-Image-Models-Test-November-2024",
    "uparasha/ASRtoTexttoStorytoImagestoVideo",
    "akashagarwal/ASRGenerateStory",
    "MateusA/StoryGenerator",
    "awacke1/Speeech2Text2Story2Images2Video",
    "rajatus231/Speeech2Text2Story2Images2Video",
    "ocordes/GradioSpeechToTextToMedia",
    "awacke1/GradioSpeech2Text2Story2Images2Video",
    "mm2593/Gradiospeech2Text2Story2Video",
    "manjuvallayil/te-reo",
    "awacke1/Text2SpeechSentimentSave",
    "RachAmm/Wav2vec-vs-Whisper",
    "salashvijay/audiototxttosentiment",
    "awacke1/NLPAutoAI",
    "awacke1/SpeechStoryReadAloud",
    "sandeepmajumdar/nlp-sorcery",
    "freddyaboulton/3.1.4.9-all-demos",
    "TheFriendlyNPC/French_Translation_Audio",
    "piecurus/speech_to_text",
    "ThirdIringan/Speech_Equation_Solver",
    "on1onmangoes/mango1",
    "bharathraj-v/audio-content-analysis"
  ],
  "createdAt": "2022-03-02T23:29:05.000Z",
  "safetensors": {
    "parameters": {
      "F32": 94395552
    },
    "total": 94395552
  }
}