vrclc/Whisper-small-Malayalam

imasc_openslr_festfox

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: 0.0572
• Wer: 28.1413

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: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1000
• training_steps: 6000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0795	0.41	1000	0.1409	60.0398
0.0494	0.82	2000	0.0887	43.3441
0.0272	1.23	3000	0.0731	37.3227
0.0187	1.64	4000	0.0653	34.3867
0.0089	2.06	5000	0.0583	29.8333
0.0093	2.47	6000	0.0572	28.1413

Framework versions

• Transformers 4.37.2
• Pytorch 2.1.1+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1