AI models
TC-DNN-BLSTM-DNN
Training compute
1.9×10¹⁷ FLOP
Parameters
18.4M
Published
Apr 6, 2015
TC-DNN-BLSTM-DNN is an AI model developed by Carnegie Mellon University (CMU) (United States), first published in April 2015. It works in the speech domain, on tasks such as speech recognition (asr) and speech-to-text.
Training it took an estimated 1.9×10¹⁷ FLOP of compute (estimation method: hardware). The model has 18,413,568 parameters. It was trained on roughly 29.2M datapoints. Training ran on 1 NVIDIA Tesla K20m for about 51 hours.
Access: Unreleased. Its weights are not openly released. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Carnegie Mellon University (CMU)
- Country of organization
- United States
- Domain
- Speech
- Task
- Speech recognition (ASR), Speech-to-text
- Training compute
- 1.9×10¹⁷ FLOP
- Compute estimation method
- Hardware
- Parameters
- 18,413,568
- Dataset size
- 29.2M
- Training hardware
- NVIDIA Tesla K20m
- Chips used
- 1
- Training time
- 51 h
- Training power draw
- 263 W
- Model accessibility
- Unreleased
- Open weights
- No
- Epoch confidence
- Confident
More from Carnegie Mellon University (CMU)
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