HomeIoT ModelsHuggingFace-WavLM-Base-Plus

    HuggingFace-WavLM-Base-Plus

    Real-time Speech processing.

    HuggingFaceWavLMBasePlus is a real time speech processing backbone based on Microsoft's WavLM model.

    Qualcomm® QCS8550
    QCS8550 (Proxy)
    TorchScriptTFLite
    929ms
    Inference Time
    143-151MB
    Memory Usage
    811CPU
    Layers

    Technical Details

    Model checkpoint:wavlm-libri-clean-100h-base-plus
    Input resolution:1x320000
    Number of parameters:95.1M
    Model size:363 MB

    Applicable Scenarios

    • Smart Home
    • Accessibility

    Licenses

    Source Model:MIT
    Deployable Model:AI Model Hub License

    Tags

    • backbone
      A “backbone” model is designed to extract task-agnostic representations from specific data modalities (e.g., images, text, speech). This representation can then be fine-tuned for specialized tasks.

    Supported IoT Devices

    • QCS8550 (Proxy)

    Supported IoT Chipsets

    • Qualcomm® QCS8550