Inference Providers documentation
Audio Classification
Audio Classification
Audio classification is the task of assigning a label or class to a given audio.
Example applications:
- Recognizing which command a user is giving
- Identifying a speaker
- Detecting the genre of a song
For more details about the audio-classification task, check out its dedicated page! You will find examples and related materials.
Recommended models
Explore all available models and find the one that suits you best here.
Using the API
There are currently no snippet examples for the audio-classification task, as no providers support it yet.
API specification
Request
| Headers | ||
|---|---|---|
| authorization | string | Authentication header in the form 'Bearer: hf_****' when hf_**** is a personal user access token with “Inference Providers” permission. You can generate one from your settings page. |
| Payload | ||
|---|---|---|
| inputs* | string | The input audio data as a base64-encoded string. If no parameters are provided, you can also provide the audio data as a raw bytes payload. |
| parameters | object | |
| function_to_apply | enum | Possible values: sigmoid, softmax, none. |
| top_k | integer | When specified, limits the output to the top K most probable classes. |
Response
| Body | ||
|---|---|---|
| (array) | object[] | Output is an array of objects. |
| label | string | The predicted class label. |
| score | number | The corresponding probability. |