metadata

language:
  - uk
license: apache-2.0
tags:
  - whisper-event
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
  - google/fleurs
model-index:
  - name: whisper-large-uk
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 11.0
          type: mozilla-foundation/common_voice_11_0
          config: uk
          split: test
          args: uk
        metrics:
          - name: Wer
            type: wer
            value: 10.02262314404669
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Fleurs
          type: google/fleurs
          config: uk_ua
          split: test
          args: uk_ua
        metrics:
          - name: Wer
            type: wer
            value: 7.564370215727209

whisper-large-uk

This model is a fine-tuned version of openai/whisper-large-v2 on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

eval_loss: 0.2527
eval_wer: 10.0226
eval_runtime: 9610.7996
eval_samples_per_second: 0.747
eval_steps_per_second: 0.023
epoch: 1.8
step: 1098

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: 5e-06
train_batch_size: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
training_steps: 1500
mixed_precision_training: Native AMP

Framework versions

Transformers 4.26.0.dev0
Pytorch 1.13.1+cu117
Datasets 2.8.0
Tokenizers 0.13.2