Model Card for Ratchet + Whisper Large V2

Whisper Large V3 should be preferred for transcription quality. If you're looking for better performance, check out Distil Whisper Large V3

This is a conversion from the GGML format of openai/whisper-large-v2 into the Ratchet custom format.

Model Card Contact

GGUF

Model size

2B params

Architecture

Hardware compatibility

We're not able to determine the quantization variants.

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support