1ytic/pytorch-edit-distance
Levenshtein edit-distance on PyTorch and CUDA
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.
Stars
93
Forks
13
Language
Cuda
License
MIT
Category
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.
Higher-rated alternatives
TensorSpeech/TensorFlowASR
:zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2....
dangvansam/viet-asr
VietASR - Vietnamese Automatic Speech Recognition
wenet-e2e/wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit
xinjli/allosaurus
Allosaurus is a pretrained universal phone recognizer for more than 2000 languages
srvk/eesen
The official repository of the Eesen project