Edit model card

whisper-small-pt-1000h

This model is a fine-tuned version of openai/whisper-small on the fsicoli/cv17-fleurs-coraa-mls-ted-alcaim-cf-cdc-lapsbm-lapsmail-sydney-lingualibre-voxforge-tatoeba default dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3036
  • Wer: 0.1490

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: 5e-06
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 10000
  • training_steps: 182000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.2594 1.58 160000 0.6842 0.1525
0.3036 1.77 180000 0.6491 0.1490

Framework versions

  • Transformers 4.39.0.dev0
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.1.dev0
  • Tokenizers 0.15.0
Downloads last month
10
Safetensors
Model size
242M params
Tensor type
F32
·

Finetuned from

Evaluation results

  • Wer on fsicoli/cv17-fleurs-coraa-mls-ted-alcaim-cf-cdc-lapsbm-lapsmail-sydney-lingualibre-voxforge-tatoeba default
    self-reported
    0.149