IletheK/mjw-whisper-base

Whisper Base Karbi ASR - Ilethe

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

• Loss: 1.0595
• Wer: 170.5279

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: 32
• eval_batch_size: 16
• seed: 42
• 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: 50
• training_steps: 300
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.2737	5.8824	100	0.9795	86.9501
0.3263	11.7647	200	1.0189	125.8065
0.1461	17.6471	300	1.0595	170.5279

Framework versions

• Transformers 5.16.1
• Pytorch 2.11.0+cu128
• Datasets 4.8.5
• Tokenizers 0.23.1