whisper-small-p_p – AI Model by philtoms | AlphaNeural AI

You can deploy this model and start earning money today!

philtoms/
whisper-small-p_p

like

0

generated_from_trainer

mozilla-foundation/common_voice_11_0

openai/whisper-small

Views

No views yet

whisper-small-p_p

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

Loss: 0.5325

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: 0.001
train_batch_size: 5
eval_batch_size: 2
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_steps: 50
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	3	1.2985
No log	2.0	6	1.1802
No log	3.0	9	1.0410
No log	4.0	12	0.9306
No log	5.0	15	0.7931
No log	6.0	18	0.6524
No log	7.0	21	0.5394
No log	8.0	24	0.5266
0.7465	9.0	27	0.4996
0.7465	10.0	30	0.5325

Framework versions

PEFT 0.15.2
Transformers 4.53.0
Pytorch 2.6.0+cu124
Datasets 2.14.4
Tokenizers 0.21.2