AI models
BiLSTM for Speech
Training compute
2.4×10¹³ FLOP
Parameters
152.1K
Published
Aug 1, 2005
BiLSTM for Speech is an AI model developed by IDSIA and Technical University of Munich (Switzerland and Germany), first published in August 2005. It works in the speech domain, on tasks such as speech recognition (asr).
Training it took an estimated 2.4×10¹³ FLOP of compute (estimation method: third-party estimation). The model has 152,061 parameters.
The reference paper has 4,706 citations. Epoch AI rates the confidence of this record as likely.
Full record
- Organization
- IDSIA, Technical University of Munich
- Country of organization
- Switzerland, Germany
- Domain
- Speech
- Task
- Speech recognition (ASR)
- Training compute
- 2.4×10¹³ FLOP
- Compute estimation method
- Third-party estimation
- Parameters
- 152,061
- Citations
- 4,706
- Epoch confidence
- Likely
More from IDSIA,Technical University of Munich
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