steja's picture
somali whisper large ft
c74cf12
metadata
license: apache-2.0
tags:
  - whisper-event
  - generated_from_trainer
datasets:
  - google/fleurs
metrics:
  - wer
model-index:
  - name: Whisper_large_Somali
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: google/fleurs so_so
          type: google/fleurs
          config: so_so
          split: test
        metrics:
          - name: Wer
            type: wer
            value: 55.04238164151334

Whisper_large_Somali

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

  • Loss: 2.0039
  • Wer: 55.0424

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: 8
  • eval_batch_size: 16
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 64
  • total_eval_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 100
  • training_steps: 1000

Training results

Training Loss Epoch Step Validation Loss Wer
0.0012 38.44 500 1.8906 55.4145
0.0004 76.89 1000 2.0039 55.0424

Framework versions

  • Transformers 4.25.1
  • Pytorch 1.13.0+cu117
  • Datasets 2.7.1
  • Tokenizers 0.13.2