whisper-phoneme-fine-tuning – AI Model by ChristineCPC | AlphaNeural AI

You can deploy this model and start earning money today!

ChristineCPC/
whisper-phoneme-fine-tuning

like

0

openai/whisper-small

Views

No views yet

whisper-phoneme-fine-tuning

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

Loss: 1.7291

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
gradient_accumulation_steps: 2
total_train_batch_size: 16
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: 50
training_steps: 500
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
9.7825	0.1208	100	4.4487
5.7128	0.2415	200	2.6052
3.9927	0.3623	300	1.9682
3.5450	0.4831	400	1.7654
3.3930	0.6039	500	1.7291

Framework versions

PEFT 0.18.1
Transformers 5.0.0
Pytorch 2.10.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2