gyeongsan_1_6_model_2000 – AI Model by lalok | AlphaNeural AI | AlphaNeural AI

You can deploy this model and start earning money today!

lalok/
gyeongsan_1_6_model_2000

like

0

automatic-speech-recognition

generated_from_trainer

openai/whisper-medium

endpoints_compatible

Views

No views yet

gyeongsan_1_6_model_2000

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

Loss: 0.1514
Cer: 10.5865

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 100
training_steps: 20000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
0.2344	0.0450	2000	0.2203	12.7562
0.2228	0.0901	4000	0.2065	12.7230
0.1923	0.1351	6000	0.1928	11.7444
0.1624	0.1801	8000	0.1829	11.3387
0.1663	0.2252	10000	0.1767	11.3328
0.1766	0.2702	12000	0.1696	11.1766
0.1553	0.3152	14000	0.1633	10.9184
0.1359	0.3603	16000	0.1581	10.6428
0.1551	0.4053	18000	0.1537	10.6719
0.1373	0.4503	20000	0.1514	10.5865

Framework versions

Transformers 4.41.2
Pytorch 2.2.2+cu121
Datasets 2.19.2
Tokenizers 0.19.1