<!-- 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 finetuned for ceb

This model is a fine-tuned version of openai/whisper-tiny on the Fleurs Ceb subset dataset. It achieves the following results on the evaluation set:

• eval_loss: 1.5317
• eval_wer: 377.5941
• eval_wer_un_norm: 392.3268
• eval_bleu: 0.8925
• eval_bleu_un_norm: 0.7824
• eval_runtime: 2243.8773
• eval_samples_per_second: 0.679
• eval_steps_per_second: 0.085
• epoch: 2.09
• step: 1600

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: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: reduce_lr_on_plateau
• lr_scheduler_warmup_steps: 2000
• training_steps: 20000
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.35.0.dev0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1