metadata
language:
- ko
license: apache-2.0
base_model: openai/whisper-small
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_13_0
metrics:
- wer
model-index:
- name: Whisper Small KO
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 13.0
type: mozilla-foundation/common_voice_13_0
config: ko
split: test
args: 'config: ko, split: test'
metrics:
- name: Wer
type: wer
value: 0.9687814702920443
Whisper Small KO
This model is a fine-tuned version of openai/whisper-small on the Common Voice 13.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3779
- Cer: 1.0055
- Wer: 0.9688
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer | Wer |
|---|---|---|---|---|---|
| 0.2858 | 5.26 | 100 | 0.4512 | 1.1681 | 0.9869 |
| 0.0058 | 10.53 | 200 | 0.3578 | 1.0637 | 0.8610 |
| 0.0012 | 15.79 | 300 | 0.3699 | 0.9535 | 0.9225 |
| 0.0009 | 21.05 | 400 | 0.3759 | 1.0149 | 0.9809 |
| 0.0008 | 26.32 | 500 | 0.3779 | 1.0055 | 0.9688 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1