Llama-AVSR
Reported on 2 benchmarks across 2 tasks · 1 paper
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Audio1 result
- Word Error Rate (WER)· uses extra data· 2024-09-180.81best: 0.68 (Whisper)
Speech1 result
- Word Error Rate (WER)· uses extra data· 2024-09-180.77best: 0.74 (MMS-LLaMA)