auro/whisper-cli-small-or

Whisper Small Odia

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

• Loss: 0.4245
• Wer: 27.0240

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: 32
• 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
0.0021	49.0	1000	0.4245	27.0240
0.0001	99.0	2000	0.7338	28.1241
0.0	149.0	3000	0.8594	28.6601
0.0	199.0	4000	0.9103	28.3498
0.0	249.0	5000	0.9329	28.2934

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.13.0
• Datasets 2.7.1
• Tokenizers 0.13.2