Model card
Universal-1.
AssemblyAIproprietaryTransformer2 current SOTA
AssemblyAI Universal-1: multi-domain ASR model released April 2024. Evaluated on LibriSpeech, AMI, Earnings-22, and other benchmarks.
§ 02 · Benchmarks
Every benchmark Universal-1 has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | LibriSpeech | Speech · Speech Recognition | wer-test-clean | 1.6% | #1 | 2024-04-03 | source ↗ |
| 02 | LibriSpeech | Speech · Speech Recognition | wer-test-other | 3.1% | #1 | 2024-04-03 | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 04 · Papers
1 paper with results for Universal-1.
- 2024-04-03· Speech· 2 results
Universal-1: AssemblyAI Speech Foundation Model
AssemblyAI Research
§ 06 · Sources & freshness
Where these numbers come from.
official
2
results
2 of 2 rows marked verified.