metadata
language:
- sv
license: apache-2.0
tags:
- hf-asr-leaderboard
- generated_from_trainer
metrics:
- wer
model-index:
- name: Whisper Small - Swedish
results: []
Whisper Small - Swedish
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3011
- Wer: 19.8220
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-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- 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: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1353 | 1.94 | 1500 | 0.2815 | 20.8357 |
| 0.019 | 3.89 | 3000 | 0.3011 | 19.8220 |
Framework versions
- Transformers 4.25.0.dev0
- Pytorch 1.12.1
- Datasets 2.7.1
- Tokenizers 0.13.2