whisper-base-ft-cv-cy

This model is a fine-tuned version of openai/whisper-base on the DewiBrynJones/commonvoice_18_0_cy train_all+other_with_excluded main dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5415
  • Wer: 0.4117

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
0.5465 1.4144 1000 0.6223 0.4702
0.3781 2.8289 2000 0.5415 0.4117

Framework versions

  • Transformers 4.46.2
  • Pytorch 2.5.1+cu124
  • Datasets 3.1.0
  • Tokenizers 0.20.3
Downloads last month
18
Safetensors
Model size
72.6M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for DewiBrynJones/whisper-base-ft-cv-cy

Finetuned
(380)
this model