Audio domain

Audio-domain metrics are essential for assessing the performance of models in tasks such as speech recognition, audio classification, and sound event detection. TorchMetrics offers a comprehensive set of specialized metrics tailored for these audio-specific purposes. Utilizing these metrics from TorchMetrics aids in the development of more accurate and resilient audio-based models, ensuring that performance evaluations are both meaningful and directly applicable to real-world audio tasks.

Evaluating Speech Quality with PESQ metric

Evaluating Speech Quality with PESQ metric

Signal-to-Noise Ratio

Signal-to-Noise Ratio

Image domain

Image-domain metrics are pivotal for gauging the performance of models in tasks like object detection, and segmentation. TorchMetrics provides a suite of specialized metrics designed for these purposes. Using these image-specific metrics from Torch Metrics helps in developing more precise and robust image-based models, ensuring that performance evaluations are both meaningful and directly applicable to practical vision tasks.

Spatial Correlation Coefficient

Spatial Correlation Coefficient

CLIPScore

CLIPScore

Text domain

Text-domain metrics are essential for evaluating the performance of models in tasks like text classification, summarization, and translation. TorchMetrics provides a suite of specialized metrics designed for these purposes. Using these text-specific metrics from Torch Metrics helps in developing more precise and robust text-based models, ensuring that performance evaluations are both meaningful and directly applicable to practical NLP tasks.

Perplexity

Perplexity

BERTScore

BERTScore

ROUGE

ROUGE

Gallery generated by Sphinx-Gallery