Audio AI labeling not working? (HuggingFace)

Report bugs
#1

I tried audio AI labeling with simple file. I created HuggingFace API key with full RW permissions. (Yes, I tried to recreate Access Token many times with different permissions, although I only need the inference permissions) I immediately get error:

Creating job... OK (ID: 38900767)

✔️ Job scheduled at 15 Oct 2025 04:02:56
✔️ Job started at 15 Oct 2025 04:02:57
Labeling data using Audio Spectrogram Transformers

Detecting audio:
    Audioset labels: bang
    Other label: other
    Min. confidence: 0.2
    Window size: 100ms.
    Window stride: 50ms.
    IDs: 2298476597

Project ID: 794522
[1/1] Labeling test (ID 2298476597), length=795ms:
    [0 - 100ms.] Traceback (most recent call last):
  File "/usr/local/lib/python3.8/dist-packages/requests/models.py", line 971, in json
    return complexjson.loads(self.text, **kwargs)
  File "/usr/lib/python3.8/json/__init__.py", line 357, in loads
    return _default_decoder.decode(s)
  File "/usr/lib/python3.8/json/decoder.py", line 337, in decode
    obj, end = self.raw_decode(s, idx=_w(s, 0).end())
  File "/usr/lib/python3.8/json/decoder.py", line 355, in raw_decode
    raise JSONDecodeError("Expecting value", s, err.value) from None
json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "transform.py", line 360, in <module>
    intervals_list = create_splits_and_classify_from_wav(
  File "transform.py", line 230, in create_splits_and_classify_from_wav
    classification = classify_audio_sample(output_file, hf_api_key)
  File "transform.py", line 144, in classify_audio_sample
    body = response.json()
  File "/usr/local/lib/python3.8/dist-packages/requests/models.py", line 975, in json
    raise RequestsJSONDecodeError(e.msg, e.doc, e.pos)
requests.exceptions.JSONDecodeError: Expecting value: line 1 column 1 (char 0)
Application exited with code 1
Job failed (see above)
#2

Hey, it looks like the AudioSet model was removed… https://api-inference.huggingface.co/models/MIT/ast-finetuned-audioset-10-10-0.4593 (404s).

Let’s see if we can find an alternative quickly.

#3

Hmm… I think HF might have retired their own inference APIs in favor of Inference Providers…