jimjakdiend's picture
Upload tokenizer
7d10d87 verified
metadata
license: mit
tags:
  - generated_from_trainer
base_model: distil-whisper/distil-large-v3
model-index:
  - name: distilwhisper_finetune
    results: []

distilwhisper_finetune

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

  • eval_loss: 0.0432
  • eval_wer: 3.2604
  • eval_runtime: 848.1823
  • eval_samples_per_second: 0.825
  • eval_steps_per_second: 0.104
  • epoch: 1.7857
  • step: 250

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: 20
  • 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: 100
  • training_steps: 1000
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.41.0
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1