v1

latestOpenAPI 3.0.32026-07-26451985.7 KB

audio-classification

Classify audio clips into predefined categories such as speech emotion, sound detection, and music genres

post/models/v2/aaraki/wav2vec2-base-finetuned-ks

Request body

urlstring required

base64string

Example request

{
  "url": "https://huggingface.co/datasets/huggingfacejs/tasks/resolve/main/audio-classification/audio.wav",
  "base64": "data:audio/wav;base64,...BASE_64_GOES_HERE (Only use this is you are not using a url)"
}

Response

Successful audio-classification response.

errorstring nullable required

Null on success; otherwise an error message.

Example response

{
  "output": [
    {
      "score": 0.12049942463636398,
      "label": "no"
    },
    {
      "score": 0.11662919074296951,
      "label": "down"
    },
    {
      "score": 0.1127392128109932,
      "label": "_unknown_"
    },
    {
      "score": 0.10831832140684128,
      "label": "stop"
    },
    {
      "score": 0.10017725080251694,
      "label": "go"
    },
    {
      "score": 0.09701883047819138,
      "label": "left"
    },
    {
      "score": 0.07834923267364502,
      "label": "on"
    },
    {
      "score": 0.07112456858158112,
      "label": "right"
    },
    {
      "score": 0.06147514656186104,
      "label": "off"
    },
    {
      "score": 0.04827316105365753,
      "label": "yes"
    },
    {
      "score": 0.047529637813568115,
      "label": "up"
    },
    {
      "score": 0.03786593675613403,
      "label": "_silence_"
    }
  ]
}