metadata

license: apache-2.0
base_model: BauyrjanQ/whisper-kk
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: whisper-kk-b4-ms1000-b
    results: []

whisper-kk-b4-ms1000-b

This model is a fine-tuned version of BauyrjanQ/whisper-kk on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.4178
Wer: 96.9956

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: 4
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 1000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.1263	0.06	1000	0.4178	96.9956

Framework versions

Transformers 4.31.0
Pytorch 2.0.1+cu117
Datasets 2.13.1
Tokenizers 0.13.3