ced-small

>>> from transformers import AutoModelForAudioClassification, AutoFeatureExtractor

>>> model_name = "mispeech/ced-small"
>>> feature_extractor = AutoFeatureExtractor.from_pretrained(model_name, trust_remote_code=True)
>>> model = AutoModelForAudioClassification.from_pretrained(model_name, trust_remote_code=True)

>>> import torchaudio
>>> audio, sampling_rate = torchaudio.load("/path-to/JeD5V5aaaoI_931_932.wav")
>>> assert sampling_rate == 16000
>>> inputs = feature_extractor(audio, sampling_rate=sampling_rate, return_tensors="pt")

>>> import torch
>>> with torch.no_grad():
...     logits = model(**inputs).logits

>>> predicted_class_id = torch.argmax(logits, dim=-1).item()
>>> model.config.id2label[predicted_class_id]
'Finger snapping'

>>> from optimum.onnxruntime import ORTModelForAudioClassification

>>> model_name = "mispeech/ced-small"
>>> model = ORTModelForAudioClassification.from_pretrained(model_name, trust_remote_code=True)

>>> import torchaudio
>>> audio, sampling_rate = torchaudio.load("/path-to/JeD5V5aaaoI_931_932.wav")
>>> assert sampling_rate == 16000
>>> input_name = model.session.get_inputs()[0].name
>>> output = model(**{input_name: torch.randn(1, 16000)})
>>> logits = output.logits.squeeze()
>>> for idx in logits.argsort()[-2:][::-1]:
>>>   print(f"{model.config.id2label[idx]}: {logits[idx]:.4f}")
'Finger snapping: 0.9155'
'Slap: 0.0567'