AI models
F5-TTS
Training compute
4.5×10²⁰ FLOP
Parameters
335.8M
Published
Dec 15, 2024
F5-TTS is an AI model developed by Shanghai Jiao Tong University, University of Cambridge and Geely Automobile Research Institute (Ningbo) Company (China and United Kingdom), first published in December 2024. It works in the speech domain, on tasks such as speech synthesis and translation.
Training it took an estimated 4.5×10²⁰ FLOP of compute (estimation method: hardware). The model has 335,800,000 parameters. It was trained on roughly 27.3B datapoints. Training ran on 8 NVIDIA A100 SXM4 80 GB for about 168 hours.
Access: Open weights (non-commercial). Its weights are openly available. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Shanghai Jiao Tong University, University of Cambridge, Geely Automobile Research Institute (Ningbo) Company
- Country of organization
- China, United Kingdom
- Domain
- Speech
- Task
- Speech synthesis, Translation
- Training compute
- 4.5×10²⁰ FLOP
- Compute estimation method
- Hardware
- Parameters
- 335,800,000
- Dataset size
- 27.3B
- Training hardware
- NVIDIA A100 SXM4 80 GB
- Chips used
- 8
- Training time
- 168 h
- Training power draw
- 6.3 kW
- Model accessibility
- Open weights (non-commercial)
- Open weights
- Yes
- Epoch confidence
- Confident
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