You can deploy this model and start earning money today!

ManyaGupta/
distil-medium.en-ft-children-with-sli

Name: distil-medium.en-ft-children-with-sli
Rating: 2.5 (6 reviews)

generated_from_trainer

distil-whisper/distil-medium.en

finetune

mit

endpoints_compatible

Views

No views yet

distil-medium.en-ft-children-with-sli

This model is a fine-tuned version of distil-whisper/distil-medium.en on the ChildrenSLIDataset dataset. It achieves the following results on the evaluation set:

Loss: 0.0456
Accuracy: 0.9960
F1: 0.9958
Precision: 0.9968
Recall: 0.9949

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: 5e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.0001	1.0	504	0.2825	0.9643	0.9619	0.9722	0.9545
0.0009	2.0	1008	0.0834	0.9881	0.9875	0.9884	0.9866
0.0002	3.0	1512	0.0442	0.9921	0.9917	0.9935	0.9899
0.0001	4.0	2016	0.1658	0.9762	0.9751	0.9736	0.9768
0.0	5.0	2520	0.0390	0.9960	0.9958	0.9968	0.9949
0.0	6.0	3024	0.0420	0.9960	0.9958	0.9968	0.9949
0.0	7.0	3528	0.0436	0.9960	0.9958	0.9968	0.9949
0.0	8.0	4032	0.0446	0.9960	0.9958	0.9968	0.9949
0.0	9.0	4536	0.0452	0.9960	0.9958	0.9968	0.9949
0.0	10.0	5040	0.0456	0.9960	0.9958	0.9968	0.9949

Framework versions

Transformers 4.42.0.dev0
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1

ManyaGupta/distil-medium.en-ft-children-with-sli

distil-medium.en-ft-children-with-sli

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

ManyaGupta/
distil-medium.en-ft-children-with-sli