NEWAgents can now see video via MCP.Try it now →
    Models/Automatic Speech Recognition/nvidia/diar_streaming_sortformer_4spk-v2.1
    Automatic Speech Recognitionnemoother

    diar_streaming_sortformer_4spk-v2.1

    by nvidia

    19Kdl/month
    64likes
    HuggingFaceUse in Pipeline
    Identifier
    Model ID
    nvidia/diar_streaming_sortformer_4spk-v2.1

    Tags

    nemospeaker-diarizationspeaker-recognitionspeechaudioTransformerFastConformerConformerNESTpytorchNeMoautomatic-speech-recognitiondataset:fisher_englishdataset:NIST_SRE_2004-2010dataset:librispeechdataset:ami_meeting_corpusdataset:voxconverse_v0.3dataset:icsidataset:aishell4dataset:dihard_challenge-3-devdataset:NIST_SRE_2000-Disc8_split1dataset:NOTSOFAR1dataset:Alimeeting-traindataset:DiPCoarxiv:2409.06656arxiv:2507.18446arxiv:2408.13106arxiv:2305.05084arxiv:2310.12371arxiv:2507.09226

    Use diar_streaming_sortformer_4spk-v2.1 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

    Organizationnvidia
    TaskAutomatic Speech Recognition
    Librarynemo
    Licenseother
    Downloads/mo19K
    Likes64

    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