whisper-small-hindi-joshtalks

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

• Loss: 0.4028
• Wer: 40.3610

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: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 50
• training_steps: 500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.348	0.9025	500	0.4028	40.3610

Framework versions

• Transformers 4.44.2
• Pytorch 2.10.0+cu128
• Datasets 4.8.3
• Tokenizers 0.19.1