• 3 % discount on prepayment
  • Insured shipping from Switzerland
  • Sustainable: refurbished instead of new
  • Warranty on all cards
← Back to overview

whisper-large-v3-turbo

OpenAI
GermanMIT

Converts speech to text. 2 sizes from 800M to 1.5B parameters.

Settings

For this model we show curated VRAM values for FP16 and FP8.

Recommendation
1× Tesla V100 16 GB

The model needs about 2.8 GB of memory. Passively cooled, fan and 8-pin EPS cable required.

Weights
1.3 GB

More suitable configurations

CardQuantityStatus
Tesla T4 16 GB1×2-3 weeks delivery time
Tesla P100 16 GB1×2-3 weeks delivery time
Tesla P40 24 GB1×2-3 weeks delivery time
Tesla V100 16 GB1×in stock
Tesla V100 32 GB1×On order, delivery time approx. 1 week
AMD Instinct MI50 16 GB1×in stock
AMD Instinct MI50 32 GB1×in stock
AMD Instinct MI60 32 GB1×2-3 weeks delivery time
AMD Instinct MI100 32 GB1×2-3 weeks delivery time
A30 24 GB1×2-3 weeks delivery time
RTX A5000 24 GB1×2-3 weeks delivery time
A40 48 GB1×2-3 weeks delivery time