Hugging Face's logo

crossdelenna
/
whisperturbo

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
whisperturbo / README.md
crossdelenna's picture
crossdelenna
End of training
d7d641d verified
preview code
|
raw
history blame
1.42 kB
metadata
library_name: peft
license: mit
base_model: openai/whisper-large-v3-turbo
tags:
  - generated_from_trainer
model-index:
  - name: whisperturbo
    results: []

whisperturbo

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

  • eval_loss: 0.5575
  • eval_runtime: 1342.9546
  • eval_samples_per_second: 2.137
  • eval_steps_per_second: 0.267
  • epoch: 0.5571
  • step: 400

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: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Use 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: 50
  • training_steps: 1200
  • mixed_precision_training: Native AMP

Framework versions

  • PEFT 0.14.0
  • Transformers 4.46.3
  • Pytorch 2.5.1+cu121
  • Datasets 3.1.0
  • Tokenizers 0.20.3