Hugging Face's logo

FluidInference
/
campplus-coreml

Audio Classification
Core ML
Chinese
ane
speaker-verification
speaker-diarization
campplus
funasr
fluidaudio
Model card Files
xet
 Community
campplus-coreml

Commit History

2 days ago

  1. docs: v2 files, host mean normalization, AMI benchmark and Changelog (FluidAudio #985)⁠

    alexwengg
    Verified signature
    f316edb

  2. Add CamPlusPreprocessor_v2 + CamPlusPlus_v2: Kaldi-exact fbank, exact segment pooling, fp32 (FluidAudio #985)⁠

    alexwengg
    Verified signature
    b7be41f

  1. Add config.json

    alexwengg
    Verified signature
    321b18e

  1. docs: AISHELL EER 0.48%

    alexwengg
    Verified signature
    daa02e7

  2. Fix: actually RangeDim CAM++ (clean overwrite)

    alexwengg
    Verified signature
    0c813cd

  3. Delete folder CamPlusPlus.mlmodelc with huggingface_hub

    alexwengg
    Verified signature
    36efe8a

  4. Re-convert CAM++ with dynamic time (RangeDim) for variable-length audio

    alexwengg
    Verified signature
    a5fd4ba

  5. Add CAM++ CoreML (preprocessor + speaker embedding + card)

    alexwengg
    Verified signature
    83bddac

  6. initial commit

    alexwengg
    Verified signature
    2e41cf8