syhw/wer_are_we
Attempt at tracking states of the arts and recent results (bibliography) on speech recognition.
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.
Stars
1,865
Forks
226
Language
—
License
—
Category
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.
Higher-rated alternatives
githubharald/CTCDecoder
Connectionist Temporal Classification (CTC) decoding algorithms: best path, beam search, lexicon...
githubharald/CTCWordBeamSearch
Connectionist Temporal Classification (CTC) decoder with dictionary and language model.
nl8590687/ASRT_SpeechRecognition
A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统
athena-team/athena
an open-source implementation of sequence-to-sequence based speech processing engine
hirofumi0810/tensorflow_end2end_speech_recognition
End-to-End speech recognition implementation base on TensorFlow (CTC, Attention, and MTL training)