AI models
FastSpeech
Training compute
7.2×10¹⁸ FLOP
Parameters
30.1M
Published
Nov 20, 2019
FastSpeech is an AI model developed by Zhejiang University (ZJU) and Microsoft Research (China and United States), first published in November 2019. It works in the speech domain, on tasks such as text-to-speech (tts).
Training it took an estimated 7.2×10¹⁸ FLOP of compute (estimation method: hardware). The model has 30,100,000 parameters. Training ran on 4 NVIDIA V100.
Access: Unreleased. Its weights are not openly released. Epoch AI rates the confidence of this record as likely.
Full record
- Organization
- Zhejiang University (ZJU), Microsoft Research
- Country of organization
- China, United States
- Domain
- Speech
- Task
- Text-to-speech (TTS)
- Training compute
- 7.2×10¹⁸ FLOP
- Compute estimation method
- Hardware
- Parameters
- 30,100,000
- Training hardware
- NVIDIA V100
- Chips used
- 4
- Chip-hours
- 53.12
- Training power draw
- 2.5 kW
- Model accessibility
- Unreleased
- Open weights
- No
- Epoch confidence
- Likely
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