Whisper Large
OpenAI's Whisper Large is a pre-trained, open-source audio model exceling at automatic speech recognition and speech translation, demonstrating strong generalization capabilities across various datasets and domains without requiring fine-tuning. As a Transformer-based encoder-decoder model, it leverages a sequence-to-sequence architecture, trained on an extensive 680k hours of labelled speech data.
Input
Output
Context
-
Max Output
-
Parameters
1.5B
Technical Specifications
Model TypeAudio
Context WindowNot available
Max Output TokensNot available
Parameters1.5B
Release DateSep 26, 2022
Training CutoffNot available
Licenseapache-2.0
Open SourceYes
Input Modalities
Audio
Output Modalities
Text
Capabilities
Resources & Links
Estimated GPU Requirements for Whisper Large
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.