id: whisper-large-v3-turbo
name: Whisper Large v3 Turbo
type: speech-model
task:
  - speech-to-text
  - speech-translation
language:
  - ru
  - en
  - multilingual
source: huggingface
upstream_id: openai/whisper-large-v3-turbo
upstream_url: https://huggingface.co/openai/whisper-large-v3-turbo
license: mit
status: candidate
created_at: 2026-06-19
storage_path: /models/audio/whisper-large-v3-turbo
format: safetensors
quantization: none
filename: model.safetensors
file_size_bytes: 1617824864
context_length: null
vram_required_gb: null
parameters: null
base_model: openai/whisper-large-v3
adapter_for: null
datasets: []
eval_suites: []
deployment:
  target: docker-gpu.cin.su
  runtime: transformers
  served_model_name: whisper-large-v3-turbo
notes: "ASR and speech translation model for the audio plugin."