This model is a fine-tuned version of openai/whisper-large-v3-turbo on the audiofolder dataset. It achieves the following results on the evaluation set:

Loss: 0.0987
Wer: 33.2956

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: 16
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant_with_warmup
lr_scheduler_warmup_steps: 500
training_steps: 5000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1914	0.4604	500	0.1981	54.3022
0.1291	0.9208	1000	0.1348	43.5821
0.1041	1.3812	1500	0.1196	39.9390
0.0935	1.8416	2000	0.1027	36.7426
0.0653	2.3020	2500	0.1056	36.7208
0.0619	2.7624	3000	0.1012	35.1193
0.0432	3.2228	3500	0.1034	34.7837
0.046	3.6832	4000	0.1002	34.4787
0.0335	4.1436	4500	0.0968	33.0341
0.0354	4.6041	5000	0.0987	33.2956

Framework versions

Transformers 4.46.3
Pytorch 2.4.0+cu121
Datasets 3.1.0
Tokenizers 0.20.3

bijaykumarsingh/whisper-turbo-as-LDCIL-sentence-Aligned_Dataset

whisper-turbo-as-LDCIL-sentence-Aligned_Dataset

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

bijaykumarsingh/
whisper-turbo-as-LDCIL-sentence-Aligned_Dataset