metadata

language:
  - sw
license: apache-2.0
tags:
  - whisper-event
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
base_model: openai/whisper-small
model-index:
  - name: Whisper Small Swahili
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: mozilla-foundation/common_voice_11_0 sw
          type: mozilla-foundation/common_voice_11_0
          config: sw
          split: test
          args: sw
        metrics:
          - type: wer
            value: 27.62114587994997
            name: Wer

Whisper Small Swahili

This model is a fine-tuned version of openai/whisper-small on the mozilla-foundation/common_voice_11_0 sw dataset. It achieves the following results on the evaluation set:

Loss: 0.5597
Wer: 27.6211

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: 128
eval_batch_size: 64
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 250
training_steps: 500
mixed_precision_training: Native AMP

Training results

Framework versions

Transformers 4.26.0.dev0
Pytorch 1.13.0+cu117
Datasets 2.7.1.dev0
Tokenizers 0.13.2