meg51/whisper-medium-hindi-15000

Whisper Medium Hindi -megha sharma

This model is a fine-tuned version of openai/whisper-medium on the Google Fleurs dataset. It achieves the following results on the evaluation set:

• Loss: 0.3508
• Wer: 18.4401

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: 5e-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: 1000
• training_steps: 15000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0669	3.3898	1000	0.2077	20.9098
0.0118	6.7797	2000	0.2657	19.4162
0.0026	10.1695	3000	0.2930	18.9477
0.0018	13.5593	4000	0.3045	18.3717
0.0017	16.9492	5000	0.3281	18.7134
0.0011	20.3390	6000	0.3288	18.1179
0.0005	23.7288	7000	0.3398	18.3034
0.0004	27.1186	8000	0.3515	18.5182
0.0003	30.5085	9000	0.3508	18.4401

Framework versions

• Transformers 4.43.3
• Pytorch 2.4.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1