rishabhjain16/whisper-base_to_cv_albanian

<!-- 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 tiny Albanian Test

This model is a fine-tuned version of openai/whisper-base on the Common Voice 16 Albanian dataset. It achieves the following results on the evaluation set:

• —eval_loss: 1.2684
• —eval_wer: 71.3646
• —eval_runtime: 99.9792
• —evalsamplesper_second: 3.841
• —evalstepsper_second: 0.96
• —epoch: 46.3
• —step: 2500

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: 16
• —evalbatchsize: 4
• —seed: 42
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 500
• —training_steps: 4000

Framework versions

• —Transformers 4.38.0.dev0
• —Pytorch 2.1.0+cu121
• —Datasets 2.17.1
• —Tokenizers 0.15.2