arun100/whisper-base-bn-2

Whisper Base Bengali

This model is a fine-tuned version of arun100/whisper-base-bn on the google/fleurs bn_in dataset. It achieves the following results on the evaluation set:

• Loss: 0.2509
• Wer: 43.6760

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-07
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• 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
0.2889	79.0	1000	0.2730	45.0242
0.2527	159.0	2000	0.2593	44.4617
0.2306	239.0	3000	0.2539	44.0616
0.2191	319.0	4000	0.2515	43.7367
0.2164	399.0	5000	0.2509	43.6760

Framework versions

• Transformers 4.37.0.dev0
• Pytorch 2.1.2+cu121
• Datasets 2.16.2.dev0
• Tokenizers 0.15.0