whisper-base-ha

<!-- 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 Base Ha - Eldad Akhaumere

This model is a fine-tuned version of openai/whisper-base on the Common Voice 16.0 dataset. It achieves the following results on the evaluation set:

• eval_loss: 2.5009
• eval_wer_ortho: 106.2891
• eval_wer: 104.9243
• eval_runtime: 168.7552
• eval_samples_per_second: 3.911
• eval_steps_per_second: 0.249
• epoch: 12.7389
• step: 2000

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant_with_warmup
• lr_scheduler_warmup_steps: 50
• num_epochs: 15.0
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1