Akan-3-small-2000ms – AI Model by devkyle | AlphaNeural AI

You can deploy this model and start earning money today!

devkyle/
Akan-3-small-2000ms

like

0

automatic-speech-recognition

generated_from_trainer

openai/whisper-small

endpoints_compatible

Views

No views yet

whisper-small-akan

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

Loss: 0.9537
Wer: 35.7102

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: 0.0001
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: 500
training_steps: 2000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0761	10.0	250	0.6787	41.9921
0.0557	20.0	500	0.7485	42.4731
0.0273	30.0	750	0.8616	40.3509
0.0123	40.0	1000	0.9085	38.3701
0.0024	50.0	1250	0.9378	36.7572
0.0002	60.0	1500	0.9400	36.5025
0.0001	70.0	1750	0.9507	35.9366
0.0001	80.0	2000	0.9537	35.7102

Framework versions

Transformers 4.44.2
Pytorch 2.4.0+cu121
Datasets 2.21.0
Tokenizers 0.19.1