metadata
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_6_1
metrics:
- wer
model-index:
- name: Whisper Small Frisian 1h
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 6.1
type: mozilla-foundation/common_voice_6_1
args: 'config: frisian, split: test'
metrics:
- name: Wer
type: wer
value: 38.73819283550169
Whisper Small Frisian 1h
This model is a fine-tuned version of openai/whisper-small on the Common Voice 6.1 dataset. It achieves the following results on the evaluation set:
- Loss: 0.7909
- Wer: 38.7382
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: 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: 50
- training_steps: 600
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.9012 | 1.1236 | 100 | 1.0076 | 50.6327 |
| 0.2217 | 2.2472 | 200 | 0.8082 | 42.3311 |
| 0.0728 | 3.3708 | 300 | 0.7689 | 39.8467 |
| 0.0228 | 4.4944 | 400 | 0.7767 | 38.6526 |
| 0.0099 | 5.6180 | 500 | 0.7866 | 38.7738 |
| 0.0061 | 6.7416 | 600 | 0.7909 | 38.7382 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1