wh-ft-lre5-dtstf5-adm-ga1ba16-st15k-pat3-v2 – AI Model by HouraMor | AlphaNeural AI

You can deploy this model and start earning money today!

HouraMor/
wh-ft-lre5-dtstf5-adm-ga1ba16-st15k-pat3-v2

like

0

automatic-speech-recognition

generated_from_trainer

openai/whisper-large-v3

endpoints_compatible

Views

No views yet

wh-ft-lre5-dtstf5-adm-ga1ba16-st15k-pat3-v2

This model is a fine-tuned version of openai/whisper-large-v3 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.5525
Wer: 0.2245
Cer: 0.1665

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: 16
eval_batch_size: 8
seed: 42
optimizer: Use 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: 750
training_steps: 15000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.508	0.6094	1000	0.4914	0.2531	0.1826
0.2932	1.2188	2000	0.4738	0.2820	0.2154
0.3284	1.8282	3000	0.4631	0.2275	0.1682
0.1329	2.4375	4000	0.5029	0.2349	0.1740
0.0676	3.0469	5000	0.5557	0.2168	0.1595
0.074	3.6563	6000	0.5525	0.2245	0.1665

Framework versions

Transformers 4.52.3
Pytorch 2.7.0+cu118
Datasets 3.5.1
Tokenizers 0.21.1