kawther1's picture
END
f747854 verified
metadata
license: apache-2.0
library_name: peft
tags:
  - generated_from_trainer
base_model: openai/whisper-large
datasets:
  - common_voice_16_1
metrics:
  - wer
model-index:
  - name: whisper-large-lora-final2
    results: []

whisper-large-lora-final2

This model is a fine-tuned version of openai/whisper-large on the common_voice_16_1 dataset. It achieves the following results on the evaluation set:

  • Loss: 2.2864
  • Wer Ortho: 53.0869
  • Wer: 53.0418

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: 5
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant_with_warmup
  • lr_scheduler_warmup_steps: 15
  • training_steps: 25

Training results

Training Loss Epoch Step Validation Loss Wer Ortho Wer
1.8016 0.1 25 2.2864 53.0869 53.0418

Framework versions

  • PEFT 0.11.2.dev0
  • Transformers 4.42.0.dev0
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1