metadata

license: apache-2.0
base_model: openai/whisper-base
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: whisper-base-google-fleurs-pt-br
    results: []

whisper-base-google-fleurs-pt-br

This model is a fine-tuned version of openai/whisper-base on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.4732
Wer: 18.2079

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: 2.5e-05
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: 100
training_steps: 4000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.382	0.57	400	0.4085	18.3348
0.1182	1.15	800	0.4220	17.7613
0.0991	1.72	1200	0.4479	19.6230
0.0424	2.3	1600	0.4551	18.2173
0.0458	2.87	2000	0.4732	18.2079

Framework versions

Transformers 4.36.2
Pytorch 2.1.2+cu121
Datasets 2.16.1
Tokenizers 0.15.0