Modelpublic

ElizabethMwangi/whisper-large-v3-swahili-afrivoice

sourceHugging Faceapache-2.0updated 4mo agoView on Hugging Face

0likes3downloads

Model Card

Whisper Large V3 - Swahili Afrivoice (Education Domain)

Fine-tuned version of openai/whisper-large-v3 on the Swahili Afrivoice education domain dataset.

Training Details

Parameter	Value
Base Model	openai/whisper-large-v3
Language	Swahili (sw)
Task	Transcribe
Dataset	Afrivoice Swahili - Education Domain
Max Steps	1000
Max Epochs	5
Batch Size	4
Gradient Accumulation	8 (effective batch 32)
Learning Rate	1e-5
LR Scheduler	polynomial (power: 4)
LR Warmup Steps	100
LR End	1e-8
FP16	True
SpecAugment	Enabled
Save Steps	50
Evaluation Steps	50
Max Generation Length	128

Results

Dataset	WER	CER
Afrivoice Swahili (Dev)	13.5%	4.2%
Afrivoice Swahili (Test)	13.5%	4.2%

Zero-shot on Non-Standard Speech

Dataset	WER	CER
Kenyan Swahili Non-Standard Speech	46.7%	21.7%

Usage

from transformers import pipeline

asr = pipeline("automatic-speech-recognition", model="ElizabethMwangi/whisper-large-v3-swahili-afrivoice") result = asr("audio.wav") print(result["text"])

Training Checkpoints

Saved to: /jupyterkernel/trainedmodels/swafrivoicetunewhisperlarge2/bestmodel

Citation

@misc{afrivoiceswahiliwhisper, title={Whisper Large V3 Fine-tuned on Swahili Afrivoice Education Domain}, author={Elizabeth Mwangi}, year={2026} }