arun100/whisper-small-zu_za

Whisper Small Zulu

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

• Loss: 1.1143
• Wer: 56.7866

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: 64
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• training_steps: 200
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.6219	9.01	100	1.0758	62.0201
0.0318	18.01	200	1.1143	56.7866

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.13.1+cu117
• Datasets 2.8.1.dev0
• Tokenizers 0.13.2