metadata
language:
- ko
license: apache-2.0
base_model: openai/whisper-small
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- Bingsu/zeroth-korean
metrics:
- wer
model-index:
- name: Whisper Small Ko - CookieMoster99
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: zeroth-korean
type: Bingsu/zeroth-korean
args: 'config: ko, split: test'
metrics:
- name: Wer
type: wer
value: 86.67369372082517
Whisper Small Ko - CookieMoster99
This model is a fine-tuned version of openai/whisper-small on the zeroth-korean dataset. It achieves the following results on the evaluation set:
- Loss: 0.0884
- Wer: 86.6737
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: 500
- training_steps: 4000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1053 | 0.72 | 1000 | 0.1508 | 68.2729 |
| 0.0518 | 1.44 | 2000 | 0.1074 | 80.8613 |
| 0.0136 | 2.16 | 3000 | 0.0918 | 106.6707 |
| 0.013 | 2.87 | 4000 | 0.0884 | 86.6737 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.3
- Tokenizers 0.13.3