whisper-native-children-0-dutch – AI Model by golesheed | AlphaNeural AI

You can deploy this model and start earning money today!

golesheed/
whisper-native-children-0-dutch

like

0

automatic-speech-recognition

generated_from_trainer

openai/whisper-large-v2

endpoints_compatible

Views

No views yet

Whisper Large V2

This model is a fine-tuned version of openai/whisper-large-v2 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.1401
Wer: 5.5491

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: 3e-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: 20
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.4119	0.38	30	0.1653	7.8245
0.1737	0.75	60	0.1446	5.7271
0.1437	1.12	90	0.1420	6.7487
0.0785	1.5	120	0.1317	5.1931
0.0707	1.88	150	0.1309	6.2379
0.0496	2.25	180	0.1369	5.9670
0.0318	2.62	210	0.1316	6.0367
0.0341	3.0	240	0.1290	5.5568
0.0166	3.38	270	0.1339	4.9532
0.0147	3.75	300	0.1353	5.4949
0.0109	4.12	330	0.1365	5.6342
0.0072	4.5	360	0.1402	5.4640
0.0071	4.88	390	0.1401	5.5491

Framework versions

Transformers 4.38.0.dev0
Pytorch 2.1.0+cu121
Datasets 2.14.6
Tokenizers 0.15.0