Edit model card

This is model is a finetune of the openai/whisper-small model using 750 hours of training audio from Part 3 of the National Speech Corpus. These are the final results on the evaluation set (~99 hours of audio):

Validation Loss: 0.386770
WER: 14.257934

Downloads last month: 41

Safetensors

Model size

242M params

Tensor type

F32

Inference API

Unable to determine this model's library. Check the docs .

Model tree for Xycone/whisper-small-SGspeech-finetune

Base model

openai/whisper-small

Finetuned

(1965)

this model