metadata

library_name: transformers
license: apache-2.0
base_model: openai/whisper-medium
tags:
  - generated_from_trainer
datasets:
  - fsicoli/cv18-fleurs
metrics:
  - wer
model-index:
  - name: whisper-medium-pt-cv18-fleurs2-lr
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: fsicoli/cv18-fleurs default
          type: fsicoli/cv18-fleurs
          args: default
        metrics:
          - name: Wer
            type: wer
            value: 0.0929

whisper-medium-pt-cv18-fleurs2-lr

This model is a fine-tuned version of openai/whisper-medium on the fsicoli/cv18-fleurs default dataset for Portuguese. It achieves the following results on the evaluation set:

Loss: 0.2163
Wer: 0.0929

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: 6.25e-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: 5000
training_steps: 25000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0876	2.3004	5000	0.1662	0.1059
0.0371	4.6009	10000	0.1839	0.0999
0.0246	6.9013	15000	0.2027	0.0997
0.0072	9.2017	20000	0.2152	0.0967
0.0074	11.5022	25000	0.2163	0.0929

Framework versions

Transformers 4.45.0.dev0
Pytorch 2.4.1
Datasets 2.21.0
Tokenizers 0.19.1