Hugging Face's logo

xezpeleta
/
whisper-large-eu

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Basque
whisper
whisper-event
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
whisper-large-eu / README.md
xezpeleta's picture
xezpeleta
End of training
dedcdce verified
preview code
|
raw
history blame
1.61 kB
metadata
library_name: transformers
language:
  - eu
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
  - whisper-event
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_17_0
model-index:
  - name: Whisper Large Basque
    results: []

Whisper Large Basque

This model is a fine-tuned version of openai/whisper-large-v3 on the mozilla-foundation/common_voice_17_0 eu dataset. It achieves the following results on the evaluation set:

  • eval_loss: 0.9278
  • eval_model_preparation_time: 0.0102
  • eval_wer: 44.2953
  • eval_runtime: 4165.1595
  • eval_samples_per_second: 3.272
  • eval_steps_per_second: 0.409
  • step: 0

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: 4.375e-06
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Use OptimizerNames.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: 10000
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.46.0.dev0
  • Pytorch 2.4.1+cu121
  • Datasets 3.0.2.dev0
  • Tokenizers 0.20.0