README.md

metadata

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

jinkrsmodel

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

• Loss: 1.4034
• Cer: 71.5618

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: 50
• training_steps: 400
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
0.0009	33.33	100	1.3346	48.9510
0.0005	66.67	200	1.2890	62.7040
0.0004	100.0	300	1.3687	71.0956
0.0004	133.33	400	1.4034	71.5618

Framework versions

• Transformers 4.36.0.dev0
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0