ML Research Wiki / Benchmarks / Speech Recognition / SLUE

SLUE

Speech Recognition Benchmark

Performance Over Time

📊 Showing 8 results | 📏 Metric: VoxPopuli (Dev)

Top Performing Models

Rank Model Paper VoxPopuli (Dev) Date Code
1 W2V2-B-VP100K SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech 29.90 2021-11-19 📦 asappresearch/slue-toolkit
2 HuBERT-B-LS960 SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech 19.60 2021-11-19 📦 asappresearch/slue-toolkit
3 W2V2-B-LS960 SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech 17.20 2021-11-19 📦 asappresearch/slue-toolkit
4 W2V2-B-LS960 (+ in-domain LM) SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech 15.20 2021-11-19 📦 asappresearch/slue-toolkit
5 W2V2-B-LS960 (+ TED-LIUM 3 LM) SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech 13.20 2021-11-19 📦 asappresearch/slue-toolkit
6 W2V2-L-LL60K (+ in-domain LM) SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech 11.80 2021-11-19 📦 asappresearch/slue-toolkit
7 W2V2-L-LL60K SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech 11.00 2021-11-19 📦 asappresearch/slue-toolkit
8 W2V2-L-LL60K (+ TED-LIUM 3 LM) SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech 9.10 2021-11-19 📦 asappresearch/slue-toolkit

All Papers (8)

asappresearch/slue-toolkit
asappresearch/slue-toolkit
asappresearch/slue-toolkit
asappresearch/slue-toolkit
asappresearch/slue-toolkit
asappresearch/slue-toolkit
asappresearch/slue-toolkit
asappresearch/slue-toolkit