conformer

oido

+6

Oído: open-vocabulary speech recognition that fits in a $5 ESP32-S3. 3.7% LibriSpeech WER, no cloud, no NPU.

wenet

+4

Production First and Production Ready End-to-End Speech Recognition Toolkit

PaddleSpeech

+3

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.