whisper-small-ig

<!-- 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 Igbo

This model is a fine-tuned version of openai/whisper-small on the google/fleurs-jboat dataset. It achieves the following results on the evaluation set:

• eval_loss: 1.1403
• eval_wer_ortho: 47.1588
• eval_wer: 42.9448
• eval_runtime: 397.589
• eval_samples_per_second: 2.437
• eval_steps_per_second: 0.153
• epoch: 37.0370
• step: 7000

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
• training_steps: 8000
• mixed_precision_training: Native AMP

Framework versions

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