Fastest GPU For Speech to Text

Transcribing audio, measured against realtime, which is what decides whether a long recording is a coffee break or an afternoon.

Whisper large-v3

Weights: openai/whisper-large-v3

NVIDIA L40S193.2
NVIDIA H100 80GB HBM3181.47
NVIDIA H200163.78
NVIDIA A100 40GB SXM4102.47
NVIDIA A10G86.07
NVIDIA A100 80GB SXM473.83
NVIDIA L470.11
NVIDIA T444.36

Measured in x realtime. Longer is faster.

#GPUx realtime
1NVIDIA L40S193.2
2NVIDIA H100 80GB HBM3181.47
3NVIDIA H200163.78
4NVIDIA A100 40GB SXM4102.47
5NVIDIA A10G86.07
6NVIDIA A100 80GB SXM473.83
7NVIDIA L470.11
8NVIDIA T444.36

Every number is a first-party run on our own bench. Cards missing from a board have not been measured on that model yet, or cannot fit it.