sanchit-gandhi/whisper-small-kab-1k-steps

Whisper Small Georgian

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

• Loss: 0.6125
• Wer: 53.8420

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: constant_with_warmup
• lr_scheduler_warmup_steps: 50
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.5555	1.06	1000	0.6125	53.8420

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 2.0.0.dev20221210+cu117
• Datasets 2.7.1.dev0
• Tokenizers 0.13.2