whisper-small-finetuned-gtzan – AI Model by sinanananaa | AlphaNeural AI

You can deploy this model and start earning money today!

sinanananaa/
whisper-small-finetuned-gtzan

like

0

audio-classification

generated_from_trainer

openai/whisper-small

endpoints_compatible

Views

No views yet

whisper-small-finetuned-xtreme_s

This model is a fine-tuned version of openai/whisper-small on the xtreme_s dataset. It achieves the following results on the evaluation set:

Loss: 0.0007
Accuracy: 1.0

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: 8
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	2	0.6235	1.0
No log	2.0	4	0.3568	1.0
0.4394	3.0	6	0.0600	1.0
0.4394	4.0	8	0.0103	1.0
0.0343	5.0	10	0.0033	1.0
0.0343	6.0	12	0.0017	1.0
0.0343	7.0	14	0.0011	1.0
0.0015	8.0	16	0.0009	1.0
0.0015	9.0	18	0.0008	1.0
0.0007	10.0	20	0.0007	1.0

Framework versions

Transformers 4.53.0
Pytorch 2.8.0.dev20250319+cu128
Datasets 3.6.0
Tokenizers 0.21.2