- First of its kind Sota Model from Calay -

Achieves a WER of 14.4 in test coverage

Training added up to 10 Hours With 40K samples ranging from 5 to 30 seconds of audio.

A100 + 2(T4)

Safetensors

Model size

242M params

Tensor type

F32

Inference Providers NEW

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