whisper-large-v3-turbo
Official · BF16 · safetensors
Runtime certified: Transformers
| Precision / quantization | Format | Bits | Publisher trust | Deployment state |
|---|---|---|---|---|
| BF16 | safetensors | 16 | Official | Runtime certified |
Whisper · General · Whisper v3
Whisper Large v3 Turbo: Specs, GPU requirements, hosting & deployment
Whisper Large v3 Turbo is a current Speech Recognition release in the Whisper family, certified from its immutable official source revision.
Total parameters809M
Active parametersN/A / Not directly comparable
Context windowN/A / Not directly comparable
Release statusCurrent · Current
ArchitectureEncoder-decoder speech transformer
ModalitiesAudio, Text
LicenseMIT License
Deployment stateDeployable with certified configuration
Commercial stateCommercial Use Allowed
Release date2024-10-01
Architecture, strengths and use cases
Whisper Large v3 Turbo is an official self-hostable OpenAI Audio and speech release. It uses Encoder-decoder speech transformer with 0.809B. Exact checkpoint, license, runtime, and hardware evidence is tied to the verified upstream revision.
Whisper Large v3 Turbo uses Encoder-decoder speech transformer with 0.809B. Pipeline and configuration fields are reported only where the official source publishes them.
Verified Encoder-decoder speech transformer architecture
Official checkpoint and pipeline evidence
Official BF16, Unknown checkpoint coverage
Self-hosted Audio and speech workloads
Controlled model evaluation
Production deployment planning
Certified checkpoints and quantizations
Only exact, source-certified variants attached to this release are shown.
Recommended hardware
Use only the listed runtime configurations with the exact checkpoint precision. Hardware sizing considers resident pipeline memory, runtime overhead, input and output dimensions, batch size, and safety headroom.
Estimated weight memory1.55 GB
Runtime overhead5 GB
Total with safety margin8.12 GB
Recommended best value
1× NVIDIA A100 SXM 80GB
80 GB total VRAM · nvlink
71.88 GB headroom · Available
$915.00 / monthLowest-cost viable
1× NVIDIA L4 24GB
24 GB total VRAM · pcie
15.88 GB headroom · Available
$250.00 / monthHighest performance
1× NVIDIA H200 SXM 141GB
141 GB total VRAM · nvswitch
132.88 GB headroom · Limited capacity
$2,345.00 / monthLicense and self-hosting considerations
The exact pipeline and selected precision must fit on the chosen GPUs. Requirements vary with resolution, duration, batch size, modalities, and runtime; language-model KV-cache rules are not applied.
Whisper Large v3 Turbo is published under MIT License. The release-scoped official license link and verification date are retained with the catalogue record.
Commercial Use Allowed. The official license permits commercial use; its obligations still apply.
Release timeline
openai/whisper/whisper-large-v3-turbo @ 0e6f99cdebcbaa08b7bbfad6fb36814ecf1a857def05c15a97cb81738ea78346
Frequently asked questions
How much VRAM does Whisper Large v3 Turbo require?
The estimate uses the certified checkpoint, precision, runtime, workload dimensions, batch size, and domain-specific overhead.
Which runtimes support Whisper Large v3 Turbo?
Certified upstream runtime evidence is available for transformers.
Can Whisper Large v3 Turbo be used commercially?
The stored commercial classification is Commercial Use Allowed. Consult the official MIT License terms for the final obligations.
Official references
Last verified: 2026-08-26