Speech Recognition On Ted Lium
Metriken
Word Error Rate (WER)
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | Word Error Rate (WER) | Paper Title | Repository |
|---|---|---|---|
| Whisper-LLaMa-7b | 4.6 | HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models | |
| ConformerXXL-PS | 5 | BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition | - |
0 of 2 row(s) selected.