whisper-large-v3-Telugu-Version1

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

• Loss: 0.1610
• Wer: 48.7241

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-06
• train_batch_size: 8
• 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: 2000
• training_steps: 20000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2337	6.1920	2000	0.2242	61.4168
0.1902	12.3839	4000	0.1904	55.2632
0.169	18.5759	6000	0.1778	52.8575
0.1647	24.7678	8000	0.1710	51.6746
0.1523	30.9598	10000	0.1669	50.3589
0.1383	37.1517	12000	0.1642	49.9468
0.1561	43.3437	14000	0.1628	49.3089
0.1475	49.5356	16000	0.1616	48.9234
0.1437	55.7276	18000	0.1610	48.7241
0.1395	61.9195	20000	0.1610	48.7241

Framework versions

• PEFT 0.12.1.dev0
• Transformers 4.45.0.dev0
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1