NEWVectors or files. Pick a path.Start →
    Models/Automatic Speech Recognition/BELLE-2/Belle-whisper-large-v3-zh-punct
    Automatic Speech Recognitiontransformersapache-2.0

    Belle-whisper-large-v3-zh-punct

    by BELLE-2

    Identifier
    Model ID
    BELLE-2/Belle-whisper-large-v3-zh-punct

    Tags

    transformerspytorchsafetensorswhisperautomatic-speech-recognitionbase_model:BELLE-2/Belle-whisper-large-v3-zhbase_model:finetune:BELLE-2/Belle-whisper-large-v3-zhlicense:apache-2.0endpoints_compatibleregion:us

    Use Belle-whisper-large-v3-zh-punct on Mixpeek

    Build multimodal processing pipelines with this model and others. Extract features, run inference, and set up retrieval in Mixpeek Studio.

    Open Studio

    How It Runs on Mixpeek

    On Mixpeek, Belle-whisper-large-v3-zh-punct runs as a managed extractor inside a processing pipeline. Point a bucket of automatic speech recognition data at it, and Mixpeek handles GPU provisioning, batching, retries, and writing the outputs into a vector store you can query.

    Extractor outputs land in the Mixpeek Vector Store (MVS), where you can combine them with retrieval, reranking, and filter stages to build end-to-end search and agent-perception pipelines, no model-serving infrastructure to maintain.