metadata
language:
- fi
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_13_0
metrics:
- wer
model-index:
- name: Whisper Large v3 Fine-Tuned Finnish
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 13.0
type: mozilla-foundation/common_voice_13_0
config: fi
split: test
metrics:
- name: Wer
type: wer
value: 23.707
Whisper Large v3 Fine-Tuned Finnish
This model is a fine-tuned version of openai/whisper-large-v3 on the Common Voice 13.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2178
- Wer: 23.707
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-05
- 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: polynomial
- lr_scheduler_kwargs = { 'lr_end': 1e-07 }
- training_steps: 800
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.6193 | 0.21 | 50 | 0.2905 | 29.1920 |
| 0.3171 | 0.84 | 200 | 0.3 | 27.02 |
| 0.1224 | 1.68 | 400 | 0.2906 | 28.115 |
| 0.041 | 2.53 | 600 | 0.2477 | 25.179 |
| 0.0098 | 3.37 | 800 | 0.2178 | 23.707 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.0.1
- Datasets 2.16.1
- Tokenizers 0.15.0