You can deploy this model and start earning money today!

KasuleTrevor/
cdli-whisper-lg-sulaimank-full-a40-1e-4-polynomial-10k

Name: cdli-whisper-lg-sulaimank-full-a40-1e-4-polynomial-10k
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-a40-1e-4-polynomial-10k

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: 2.9644
Wer: 0.6448
Cer: 0.3613

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: 0.0001
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: polynomial
lr_scheduler_warmup_steps: 500
training_steps: 10000

Training results

Training Loss	Epoch	Step	Cer	Validation Loss	Wer
0.9112	1.3550	500	0.3730	1.2028	0.6537
0.6527	2.7100	1000	1.0847	0.6116	0.3338
0.1781	4.0650	1500	1.7040	0.6331	0.3457
0.0744	5.4201	2000	2.2112	0.6525	0.3659
0.0385	6.7751	2500	2.5106	0.6464	0.3658
0.0101	8.1301	3000	2.7571	0.6465	0.3639
0.0047	9.4851	3500	2.8605	0.6485	0.3652
0.0009	10.8401	4000	2.9225	0.6451	0.3652
0.0014	12.1951	4500	2.9437	0.6429	0.3625
0.0009	13.5501	5000	2.9547	0.6463	0.3642
0.0007	14.9051	5500	2.9594	0.6461	0.3618
0.0009	16.2602	6000	2.9613	0.6453	0.3644
0.0007	17.6152	6500	2.9642	0.6453	0.3596
0.0008	18.9702	7000	2.9649	0.6439	0.3606
0.0009	20.3252	7500	2.9649	0.6447	0.3603
0.0007	21.6802	8000	2.9654	0.6471	0.3638
0.0008	23.0352	8500	2.9654	0.6441	0.3617
0.0008	24.3902	9000	2.9653	0.6438	0.3612
0.0007	25.7453	9500	2.9659	0.6450	0.3616
0.0007	27.1003	10000	2.9644	0.6448	0.3613

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-a40-1e-4-polynomial-10k

cdli-whisper-lg-sulaimank-full-a40-1e-4-polynomial-10k

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

KasuleTrevor/
cdli-whisper-lg-sulaimank-full-a40-1e-4-polynomial-10k