# High-precision audio classification

A cry detection model fine-tuned based on the distilhubert architecture, achieving outstanding performance on the evaluation set with an accuracy of 98.83%

A Deepfake audio detection model fine-tuned on audio folder datasets, capable of efficiently identifying synthetic speech with an evaluation accuracy of 99.64%

A deepfake audio detection model fine-tuned based on facebook/wav2vec2-base, achieving 95.45% accuracy on the evaluation set

Animal sound classification model fine-tuned based on HuBERT architecture, capable of recognizing 10 types of animal calls with 95% accuracy

An audio classification model based on the wav2vec2 architecture, fine-tuned on the privateSLI dataset for age and gender recognition tasks

An audio classification model fine-tuned based on facebook/wav2vec2-base, trained on the superb dataset with 99.99% accuracy

An audio spectrogram transformer model fine-tuned on the Speech Commands v2 dataset for audio classification tasks, achieving 98.12% accuracy.

Audio classification model based on TRillsson3 architecture, fine-tuned on the superb dataset for keyword spotting tasks, achieving 91.5% accuracy.