You can deploy this model and start earning money today!

KasuleTrevor/
cdli-whisper-lg-sulaimank-full-a40

Name: cdli-whisper-lg-sulaimank-full-a40
Availability: InStock

transformers

safetensors

whisper

automatic-speech-recognition

generated_from_trainer

sulaimank/whisper-small-luganda-400hrs

finetune

apache-2.0

endpoints_compatible

Views

No views yet

cdli-whisper-lg-sulaimank-full-a40

This model is a fine-tuned version of sulaimank/whisper-small-luganda-400hrs on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 3.9543
Wer: 0.7719
Cer: 0.5066

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 10000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
6.6726	0.6784	500	7.5784	0.7733	0.5359
3.5848	1.3569	1000	4.2486	0.7862	0.5448
3.562	2.0353	1500	4.0506	0.7787	0.5257
3.4716	2.7137	2000	3.9983	0.7740	0.5143
3.461	3.3921	2500	3.9751	0.7733	0.5102
3.5007	4.0706	3000	3.9654	0.7713	0.5063
3.4861	4.7490	3500	3.9593	0.7720	0.5069
3.3462	5.4274	4000	3.9574	0.7717	0.5077
3.4079	6.1058	4500	3.9556	0.7721	0.5103
3.5209	6.7843	5000	3.9553	0.7704	0.5059
3.4181	7.4627	5500	3.9540	0.7711	0.5083
3.5183	8.1411	6000	3.9542	0.7701	0.5056
3.4288	8.8195	6500	3.9546	0.7712	0.5088
3.5175	9.4980	7000	3.9543	0.7726	0.5073
3.4427	10.1764	7500	3.9547	0.7712	0.5046
3.5145	10.8548	8000	3.9541	0.7731	0.5107
3.3778	11.5332	8500	3.9542	0.7703	0.5042
3.5463	12.2117	9000	3.9541	0.7705	0.5084
3.6705	12.8901	9500	3.9544	0.7704	0.5051
3.4083	13.5685	10000	3.9543	0.7719	0.5066

Framework versions

Transformers 4.57.6
Pytorch 2.7.1+cu118
Datasets 3.6.0
Tokenizers 0.22.2

KasuleTrevor/cdli-whisper-lg-sulaimank-full-a40

cdli-whisper-lg-sulaimank-full-a40

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

KasuleTrevor/
cdli-whisper-lg-sulaimank-full-a40