Aakali/whisper-medium-hi-translate-jee

Whisper medium-translate Hi - Aa

This model is a fine-tuned version of Aakali/whisper-medium-hi on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

• Loss: 2.4968
• Wer: 23.6842

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: 500
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0	1000.0	1000	1.2182	13.1579
0.0	2000.0	2000	1.7360	18.4211
0.0	3000.0	3000	2.1484	23.6842
0.0	4000.0	4000	2.5106	26.3158
0.0	5000.0	5000	2.4968	23.6842

Framework versions

• Transformers 4.41.0
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1