1ytic/pytorch-edit-distance

Levenshtein edit-distance on PyTorch and CUDA

40
/ 100
Emerging

This project offers tools to calculate how different two sequences of text or speech are, specifically for refining speech recognition models. It takes in predicted text from a speech model and the correct reference text, then outputs a score (like Word Error Rate) that helps evaluate and improve the model's accuracy. It's designed for researchers and engineers working on end-to-end speech recognition systems.

No commits in the last 6 months.

Use this if you are developing or training speech recognition models and need to efficiently calculate 'edit distance' metrics like Word Error Rate (WER) on large datasets using PyTorch and CUDA.

Not ideal if you are not working with speech recognition models or if you don't use PyTorch and CUDA for your computations.

speech-recognition natural-language-processing deep-learning model-evaluation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

93

Forks

13

Language

Cuda

License

MIT

Last pushed

Jan 24, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/1ytic/pytorch-edit-distance"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.