alamsher/whisper-small-sw

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: 0.6442
• Wer: 23.7246

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: 32
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2694	1.07	1000	0.5438	26.8354
0.2306	3.02	2000	0.5081	23.9231
0.0467	4.09	3000	0.5648	24.4085
0.0239	6.03	4000	0.5994	23.8634
0.0123	7.1	5000	0.6442	23.7246

Framework versions

• Transformers 4.30.0.dev0
• Pytorch 2.0.1+cu117
• Datasets 2.12.1.dev0
• Tokenizers 0.13.3