metadata

language:
  - ko
license: apache-2.0
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - unanam/mdrama
base_model: openai/whisper-small
model-index:
  - name: whisper-small-ver1
    results: []

whisper-small-ver1

This model is a fine-tuned version of openai/whisper-small on the 사극 드라마 dataset. It achieves the following results on the evaluation set:

Loss: 8.2325
Cer: 84.4150

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: 0.001
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: linear
lr_scheduler_warmup_steps: 400
training_steps: 4000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
2.9362	5.59	1000	4.0341	165.0697
0.5237	11.17	2000	5.7270	88.3566
0.1343	16.76	3000	7.0163	83.8232
0.0004	22.35	4000	8.2325	84.4150

Framework versions

Transformers 4.38.0.dev0
Pytorch 2.1.0+cu121
Datasets 2.17.1
Tokenizers 0.15.1