metadata

license: apache-2.0
base_model: arun100/whisper-small-uk-1
tags:
  - generated_from_trainer
datasets:
  - fleurs
metrics:
  - wer
model-index:
  - name: arun100/whisper-small-uk-1
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: fleurs
          type: fleurs
          config: uk_ua
          split: test
          args: uk_ua
        metrics:
          - name: Wer
            type: wer
            value: 19.491997216423105

arun100/whisper-small-uk-1

This model is a fine-tuned version of arun100/whisper-small-uk-1 on the fleurs dataset. It achieves the following results on the evaluation set:

Loss: 0.3297
Wer: 19.4920

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-07
train_batch_size: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 5000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0191	95.0	1000	0.2881	18.6848
0.0061	190.0	2000	0.3058	18.8935
0.0035	285.0	3000	0.3179	19.2276
0.0025	380.0	4000	0.3263	19.4502
0.0022	476.0	5000	0.3297	19.4920

Framework versions

Transformers 4.37.0.dev0
Pytorch 2.1.2+cu121
Datasets 2.16.2.dev0
Tokenizers 0.15.0