auro/whisper-cli-dropout-small-or

Whisper Small Odia

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

• Loss: 0.5089
• Wer: 26.0931

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: 5e-06
• 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: 200
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0	12.01	250	0.5089	26.0931
0.0	24.02	500	0.5542	26.6291
0.0	37.01	750	0.5804	26.5162
0.0	49.02	1000	0.5902	26.4598

Framework versions

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