checkpoints / README.md
jckim's picture
gglabs/stt-turbo-multilingual-test
896417c verified
metadata
library_name: peft
language:
  - multilingual
license: mit
base_model: openai/whisper-large-v3-turbo
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: Whisper Turbo Multilingual
    results: []

Whisper Turbo Multilingual

This model is a fine-tuned version of openai/whisper-large-v3-turbo on the custom_multilingual dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4791
  • Wer: 18.75

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: 2
  • eval_batch_size: 2
  • seed: 42
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 5
  • training_steps: 20
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.3929 1.0 10 0.7320 21.875
0.076 2.0 20 0.4791 18.75

Framework versions

  • PEFT 0.15.2.dev0
  • Transformers 4.46.3
  • Pytorch 2.3.1+cu121
  • Datasets 3.0.0
  • Tokenizers 0.20.3