whisper-large-no / README.md
SnorreStorjord's picture
Update README.md
c6cb2f5
|
raw
history blame
1.19 kB
metadata
language:
  - 'no'
license: apache-2.0
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - NbAiLab/NPSC
model-index:
  - name: Whisper Large NO
    results: []

WIP

Whisper Large no

This model is a fine-tuned version of openai/whisper-large on the NbAiLab/NPSC dataset.

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: 1
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • training_steps: 4000

Framework versions

  • Transformers 4.31.0.dev0
  • Pytorch 2.0.1+cu118
  • Datasets 2.13.1
  • Tokenizers 0.13.3