whisper-small-coraa-2 – AI Model by lejonck | AlphaNeural AI

You can deploy this model and start earning money today!

lejonck/
whisper-small-coraa-2

like

0

automatic-speech-recognition

generated_from_trainer

lejonck/whisper-small-coraa-l.1

endpoints_compatible

Views

No views yet

whisper-small-coraa-2

This model is a fine-tuned version of lejonck/whisper-small-coraa-l.1 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.7976
Wer: 0.3398
Cer: 0.5531

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: 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: 100
num_epochs: 12

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.7565	1.0	750	0.7834	0.3398	0.5522
0.3618	2.0	1500	0.8102	0.3532	0.5547
0.1276	3.0	2250	0.8880	0.3562	0.5572
0.0482	4.0	3000	0.9385	0.3496	0.5567
0.0159	5.0	3750	0.9646	0.3460	0.5539
0.0095	6.0	4500	0.9888	0.3402	0.5558
0.0041	7.0	5250	1.0368	0.3406	0.5562

Framework versions

Transformers 4.55.2
Pytorch 2.7.0+cu126
Datasets 4.0.0
Tokenizers 0.21.4