syhw/wer_are_we

Attempt at tracking states of the arts and recent results (bibliography) on speech recognition.

39
/ 100
Emerging

If you're an Automatic Speech Recognition (ASR) researcher, this project helps you compare the performance of different ASR models. It compiles recent research papers and their Word Error Rate (WER) scores on benchmark datasets like LibriSpeech and WSJ. The output is a clear, ranked list of models with their associated papers and key details.

1,865 stars. No commits in the last 6 months.

Use this if you need to quickly find the current state-of-the-art results for speech recognition on standard datasets or are looking for specific research papers to reference.

Not ideal if you're looking for code implementations, tutorials on building ASR models, or results on custom datasets outside of the benchmarks listed.

speech-recognition ASR NLP-research academic-benchmarking language-technology
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 21 / 25

How are scores calculated?

Stars

1,865

Forks

226

Language

License

Last pushed

Jun 27, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/syhw/wer_are_we"

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