zarifmahir21/whisper-medium-bangla

Whisper Bengali

This model is a fine-tuned version of bengaliAI/tugstugi_bengaliai-asr_whisper-medium on the Bengali ASR Chunked dataset. It achieves the following results on the evaluation set:

• Loss: 0.1679
• Wer: 22.7111

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 200
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.9391	0.9974	190	0.1959	26.3910
0.5161	1.9921	380	0.1653	22.9320
0.2441	2.9869	570	0.1679	22.7111

Framework versions

• Transformers 5.0.0
• Pytorch 2.9.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2