ORF-small-de – AI Model by rmacek | AlphaNeural AI

You can deploy this model and start earning money today!

rmacek/
ORF-small-de

like

0

generated_from_trainer

rmacek/ORF-whisper-small

openai/whisper-small

Views

No views yet

Whisper ORF Bundeslaender

This model is a fine-tuned version of openai/whisper-small on the ZIB2 Common Voice dataset. It achieves the following results on the evaluation set:

Loss: 0.7038
Wer: 27.2689

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: cosine
training_steps: 8000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.4896	1.7153	1000	0.6019	26.6961
0.3559	3.4305	2000	0.6038	26.6192
0.259	5.1458	3000	0.6216	33.8450
0.3272	6.8611	4000	0.6382	27.0730
0.2413	8.5763	5000	0.6704	31.3207
0.1691	10.2916	6000	0.6922	27.2466
0.1702	12.0069	7000	0.7008	27.3284
0.1726	13.7221	8000	0.7038	27.2689

Framework versions

PEFT 0.10.1.dev0
Transformers 4.40.0
Pytorch 2.2.1+cu121
Datasets 2.19.0
Tokenizers 0.19.1