# Industrial-grade ASR

FireRedASR is a series of open-source industrial-grade automatic speech recognition (ASR) models supporting Mandarin, Chinese dialects, and English. It achieves new state-of-the-art (SOTA) performance on public Mandarin ASR benchmarks while excelling in lyrics recognition.

This is an end-to-end automatic speech recognition system trained using the SpeechBrain framework, employing the Conformer architecture on 25,000 hours of English speech data.

XLSR-53 large model speech recognition system optimized for Polish, fine-tuned based on facebook/wav2vec2-large-xlsr-53, supports Polish automatic speech recognition

An automatic speech recognition (ASR) solution combining the pyctcdecode library with Hugging Face models, providing efficient decoding capabilities