VALL-E X

Training compute

1.2×10²¹ FLOP

Parameters

700M

Published

Mar 7, 2023

VALL-E X is an AI model developed by Microsoft (United States), first published in March 2023. It works in the speech domain, on tasks such as translation, speech synthesis, speech recognition (asr) and speech-to-speech.

Training it took an estimated 1.2×10²¹ FLOP of compute (estimation method: operation counting). The model has 700,000,000 parameters. It was trained on roughly 151.2B datapoints. Training ran on NVIDIA V100.

Access: Unreleased. Its weights are not openly released. The reference paper has 262 citations. Epoch AI rates the confidence of this record as likely.

Full record

Organization: Microsoft
Country of organization: United States
Domain: Speech
Task: Translation, Speech synthesis, Speech recognition (ASR), Speech-to-speech
Training compute: 1.2×10²¹ FLOP
Compute estimation method: Operation counting
Parameters: 700,000,000
Dataset size: 151.2B
Training hardware: NVIDIA V100
Model accessibility: Unreleased
Open weights: No
Citations: 262
Epoch confidence: Likely