thunderboltc/whisper-small-santali-ol-chiki

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

Whisper Small Santali (Ol Chiki)

This model is a fine-tuned version of openai/whisper-small on the Common Voice Scripted Speech 24.0 - Santali (Ol Chiki) dataset. It achieves the following results on the evaluation set:

• —eval_loss: 3.1085
• —evalmodelpreparation_time: 0.0257
• —eval_wer: 1.1150
• —eval_runtime: 59.2411
• —evalsamplesper_second: 2.144
• —evalstepsper_second: 0.27
• —step: 0

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
• —trainbatchsize: 8
• —evalbatchsize: 8
• —seed: 42
• —gradientaccumulationsteps: 2
• —totaltrainbatch_size: 16
• —optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 100
• —training_steps: 1000
• —mixedprecisiontraining: Native AMP

Framework versions

• —Transformers 4.57.3
• —Pytorch 2.9.0+cu126
• —Datasets 4.0.0
• —Tokenizers 0.22.1