metadata
language:
- se
license: apache-2.0
base_model: openai/whisper-small
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: Whisper Swedish
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Swedish voice 1.0
type: mozilla-foundation/common_voice_11_0
config: sv-SE
split: test
args: 'config: se, split: test'
metrics:
- name: Wer
type: wer
value: 34.02704955499986
Whisper Swedish
This model is a fine-tuned version of openai/whisper-small on the Swedish voice 1.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3715
- Wer: 34.0270
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 4000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1191 | 1.29 | 1000 | 0.3000 | 28.7973 |
| 0.0506 | 2.59 | 2000 | 0.3083 | 32.0911 |
| 0.0298 | 3.88 | 3000 | 0.3339 | 42.4242 |
| 0.0073 | 5.17 | 4000 | 0.3715 | 34.0270 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0