This model is a fine-tuned version of openai/whisper-small on the Spoken Bible Corpus: Malasar dataset. It achieves the following results on the evaluation set:

Loss: 0.0316
Wer: 35.6110

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: 32
eval_batch_size: 16
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
0.1675	0.6083	250	0.0688	52.2824
0.0941	1.2165	500	0.0480	41.7635
0.0891	1.8248	750	0.0433	46.4417
0.0502	2.4331	1000	0.0403	40.0340
0.0606	3.0414	1250	0.0332	35.7244
0.0326	3.6496	1500	0.0318	34.3351
0.0159	4.2579	1750	0.0319	33.4562
0.0276	4.8662	2000	0.0316	35.6110

Framework versions

Transformers 4.41.2
Pytorch 2.0.1+cu117
Datasets 2.16.0
Tokenizers 0.19.1