FireRedAudio: A General-Purpose Audio Language Model with Decoupled Continuous Representations for Understanding and Generation
Open paper
Benchmark
Model
Rank
Results
audio-understanding-reasoning-on-mmsu
FireRedAudio
#1
Accuracy: 83.3
speech-editing-on-ming-freeform-audio-edit-basic
FireRedAudio
#4
ZH Deletion WER: 10.82
EN Insertion WER: 4.98
EN Deletion SIM: 0.79
…
Rank counts only results with a code link.