Hugging Face's logo

Dearlie
/
whisper-base2

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Korean
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
whisper-base2 / README.md
Dearlie's picture
Dearlie
Upload processor
167393d verified
preview code
|
raw
history blame contribute delete
No virus
1.48 kB
metadata
language:
  - ko
license: apache-2.0
tags:
  - generated_from_trainer
base_model: openai/whisper-base
datasets:
  - AIHub/noise
model-index:
  - name: Whisper Base Ko - Dearlie
    results: []

Whisper Base Ko - Dearlie

This model is a fine-tuned version of openai/whisper-base on the Noise Data dataset. It achieves the following results on the evaluation set:

  • Loss: 3.4871
  • Cer: 107.7011

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: 1
  • training_steps: 2
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Cer
2.3913 2.0 2 3.4871 107.7011

Framework versions

  • Transformers 4.41.0.dev0
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.0
  • Tokenizers 0.19.1