akera's picture
update model card README.md
0191c09
metadata
license: apache-2.0
tags:
  - generated_from_trainer
model-index:
  - name: whisper-medium-acholi
    results: []

whisper-medium-acholi

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

  • eval_loss: 0.7946
  • eval_wer: 100.0
  • eval_runtime: 77.0072
  • eval_samples_per_second: 3.169
  • eval_steps_per_second: 0.208
  • epoch: 2.0
  • step: 276

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: 32
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • training_steps: 4000
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.28.0.dev0
  • Pytorch 2.0.1+cu117
  • Datasets 2.13.0
  • Tokenizers 0.13.2