FireRedASR-AED

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Audio2 results

Speech RecognitiononAISHELL-1
Params(M)· uses extra data· 2025-01-24
1100
SOTA
FireRedASR: Open-Source Industrial-Grade Mandarin Speech Recognition Models from Encoder-Decoder to LLM Integration arXiv:2501.14350
Speech RecognitiononAISHELL-1
Word Error Rate (WER)· uses extra data· 2025-01-24
0.55
SOTA
FireRedASR: Open-Source Industrial-Grade Mandarin Speech Recognition Models from Encoder-Decoder to LLM Integration arXiv:2501.14350