This is a wav2vec2-base model trained from selected bird songs in a birddb dataset.

import librosa
import torch
from transformers import Wav2Vec2ForPreTraining,Wav2Vec2Processor

sound_file = 'sample.wav'

sound_data,_ = librosa.load(sound_file, sr=16000)

model_id = "kojima-r/wav2vec2-base-birddb-small"
model = Wav2Vec2ForPreTraining.from_pretrained(model_id)

result=model(torch.tensor([sound_data]))
hidden_vecs=result.projected_states