NEWAgents can now see video via MCP.Try it now →
    Models/Automatic Speech Recognition/facebook/data2vec-audio-base-960h
    Automatic Speech Recognitiontransformersapache-2.0

    data2vec-audio-base-960h

    by facebook

    14Kdl/month
    12likes
    HuggingFaceUse in Pipeline
    Identifier
    Model ID
    facebook/data2vec-audio-base-960h

    Tags

    transformerspytorchdata2vec-audioautomatic-speech-recognitionspeechhf-asr-leaderboardendataset:librispeech_asrarxiv:2202.03555license:apache-2.0model-indexeval-resultsendpoints_compatibledeploy:azureregion:us

    Use data2vec-audio-base-960h on Mixpeek

    Build multimodal processing pipelines with this model and others. Extract features, run inference, and set up retrieval, all through the Mixpeek pipeline builder.

    Open Pipeline Builder

    Specification

    Organizationfacebook
    TaskAutomatic Speech Recognition
    Librarytransformers
    Licenseapache-2.0
    Downloads/mo14K
    Likes12

    View on HuggingFace

    See model card, files, and community discussion

    Related Automatic Speech Recognition Models

    pyannote/speaker-diarization-3.1
    10.2M
    argmaxinc/whisperkit-coreml
    8.1M
    openai/whisper-large-v3-turbo
    7.0M
    openai/whisper-large-v3
    4.9M
    jonatasgrosman/wav2vec2-large-xlsr-53-russian
    4.9M
    jonatasgrosman/wav2vec2-large-xlsr-53-portuguese
    3.8M
    MahmoudAshraf/mms-300m-1130-forced-aligner
    3.7M
    pyannote/voice-activity-detection
    2.7M