clap-htsat-fused

from datasets import load_dataset
from transformers import pipeline

dataset = load_dataset("ashraq/esc50")
audio = dataset["train"]["audio"][-1]["array"]

audio_classifier = pipeline(task="zero-shot-audio-classification", model="laion/clap-htsat-fused")
output = audio_classifier(audio, candidate_labels=["Sound of a dog", "Sound of vaccum cleaner"])
print(output)
>>> [{"score": 0.999, "label": "Sound of a dog"}, {"score": 0.001, "label": "Sound of vaccum cleaner"}]

from datasets import load_dataset
from transformers import ClapModel, ClapProcessor

librispeech_dummy = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
audio_sample = librispeech_dummy[0]

model = ClapModel.from_pretrained("laion/clap-htsat-fused")
processor = ClapProcessor.from_pretrained("laion/clap-htsat-fused")

inputs = processor(audios=audio_sample["audio"]["array"], return_tensors="pt")
audio_embed = model.get_audio_features(**inputs)