whisper-medium-pt-cv16-fleurs2

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: 0.1428
  • Wer: 0.0949

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: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 25000
  • training_steps: 25000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.2244 2.3343 5000 0.1728 0.1110
0.1471 4.6685 10000 0.1515 0.0996
0.149 7.0028 15000 0.1428 0.0949
0.0697 9.3371 20000 0.1436 0.0940
0.0374 11.6713 25000 0.1561 0.0972

Framework versions

  • Transformers 4.45.0.dev0
  • Pytorch 2.4.1
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
19
Safetensors
Model size
764M 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 fsicoli/whisper-medium-pt-cv16-fleurs2

Finetuned
(498)
this model

Evaluation results