README.md

metadata

library_name: transformers
license: apache-2.0
base_model: openai/whisper-base
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: whisper-base-ft-cv-cy-en
    results: []

whisper-base-ft-cv-cy-en

This model is a fine-tuned version of openai/whisper-base on the DewiBrynJones/commonvoice_18_0_cy_en train main dataset. It achieves the following results on the evaluation set:

• Loss: 0.5813
• Wer: 1.2543

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
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 2000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.2368	0.7075	1000	0.6446	0.9660
0.8994	1.4149	2000	0.5813	1.2543

Framework versions

• Transformers 4.46.1
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.20.1