AI models
RNN 500/10 + RT09 LM (NIST RT05)
Training compute
1.3×10¹⁶ FLOP
Parameters
19.3M
Published
Sep 26, 2010
RNN 500/10 + RT09 LM (NIST RT05) is an AI model developed by Brno University of Technology and Johns Hopkins University (Czechia and United States), first published in September 2010. It works in the speech domain, on tasks such as transcription.
Training it took an estimated 1.3×10¹⁶ FLOP of compute (estimation method: operation counting). The model has 19,250,000 parameters. It was trained on roughly 5.4M datapoints.
The reference paper has 6,038 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Brno University of Technology, Johns Hopkins University
- Country of organization
- Czechia, United States
- Domain
- Speech
- Task
- Transcription
- Training compute
- 1.3×10¹⁶ FLOP
- Compute estimation method
- Operation counting
- Parameters
- 19,250,000
- Dataset size
- 5.4M
- Citations
- 6,038
- Epoch confidence
- Confident
More from Brno University of Technology,Johns Hopkins University
SourceEpoch AI, 'AI Models'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/ai-models. Licensed under CC BY 4.0.
← All ai models