Whisper Large V3 Turbo is an advanced speech recognition model, optimized for high-performance GPU inference. It is suitable for automatic speech recognition (ASR) tasks in various domains, leveraging large-scale training data for robust multilingual transcription. This model is an optimized version of whisper-large-v3-turbo designed for scenarios to enable local inference on CUDA GPUs.

Review the original model card for details on training data, evaluation metrics, license, intended uses, limitations, and bias before using the model.

• Developed by: Microsoft
• Model type: ONNX
• License: apache-2.0
• Model Description: This is a conversion of the whisper-large-v3-turbo model for local inference on CUDA GPUs.
• Disclaimer: Model is only an optimization of the base model, any risk associated with the model is the responsibility of the user of the model. Please verify and test for your scenarios. There may be a slight difference in output from the base model with the optimizations applied. Note that optimizations applied are distinct from fine tuning and thus do not alter the intended uses or capabilities of the model.

See Hugging Face model Whisper Large V3 Turbo for details.

Version: 1

foundryLocal : test license : apache-2.0 licenseDescription : This model is provided under the License Terms available at https://www.apache.org/licenses/LICENSE-2.0.html. author : Microsoft inputModalities : audio outputModalities : text task : automatic-speech-recognition maxOutputTokens : 2048 alias : whisper-large-v3-turbo directoryPath : cuda-fp16 promptTemplate : {"prompt": "<|startoftranscript|> <|en|> <|transcribe|> <|notimestamps|>"}

View in Studio: https://ml.azure.com/registries/azureml/models/openai-whisper-large-v3-turbo-cuda-gpu/version/1

License: apache-2.0