Edit model card

whisper-medium-pt-cv16-fleurs

This model is a fine-tuned version of openai/whisper-medium on the fsicoli/cv16-fleurs default dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1409
  • Wer: 0.0942

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-06
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 2
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 32
  • total_eval_batch_size: 2
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 5000
  • training_steps: 5000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.2552 0.93 1000 0.2200 0.1220
0.1928 1.87 2000 0.1645 0.1062
0.1646 2.8 3000 0.1508 0.1016
0.1333 3.74 4000 0.1438 0.0970
0.1027 4.67 5000 0.1409 0.0942

Framework versions

  • Transformers 4.39.0.dev0
  • Pytorch 2.2.1
  • Datasets 2.16.1
  • Tokenizers 0.15.2
Downloads last month
2
Safetensors
Model size
764M params
Tensor type
F32
·

Finetuned from

Dataset used to train fsicoli/whisper-medium-pt-cv16-fleurs

Evaluation results