English Whisper Non-Standard Small

Languages: English (en) โ€” Non-standard / accented varieties from Kenyan speakers

This model was fine-tuned on accented and non-standard Kenyan English speech to enhance ASR accuracy for regional pronunciations.

Fine-tuning data: Subset of Mozilla Common Voice + curated Kenyan English speech

๐Ÿ“Š Evaluation

Metric Dev Test
WER 0.1814 0.1209
CER 0.1034 0.0669
Downloads last month
8
Safetensors
Model size
0.2B params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for Veronica1NW/en_whisper_nonstandard_small

Finetuned
(3161)
this model

Dataset used to train Veronica1NW/en_whisper_nonstandard_small