whisper-small-sw-common-voice

This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4254
• Wer: 32.1287

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: 16
• eval_batch_size: 8
• 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: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.4533	0.43	1000	0.5533	47.3435
0.3803	0.87	2000	0.4589	36.5991
0.2228	1.3	3000	0.4405	33.3701
0.2125	1.74	4000	0.4254	32.1287

Framework versions

• Transformers 4.37.0.dev0
• Pytorch 2.1.1+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0