metadata

base_model: openai/whisper-medium
datasets:
  - Marcusxx/CngFSt3T
language:
  - ko
license: apache-2.0
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
model-index:
  - name: CngFSt3T_model
    results: []

CngFSt3T_model

This model is a fine-tuned version of openai/whisper-medium on the Marcusxx/CngFSt3T dataset. It achieves the following results on the evaluation set:

Loss: 0.0722
Cer: 13.0034

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: 250
training_steps: 3000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
0.0378	2.2321	1000	0.1281	23.0679
0.0012	4.4643	2000	0.0755	17.4412
0.0004	6.6964	3000	0.0722	13.0034

Framework versions

Transformers 4.41.2
Pytorch 2.2.2+cu121
Datasets 2.20.0
Tokenizers 0.19.1