chandan3007/whisper-small-oriya-v1.3

Whisper Small Odia v1.3

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: 0.5570
• Wer: 29.0550

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=(0.9,0.98) and epsilon=1e-06
• 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
0.0025	50.0	1000	0.4639	35.3456
0.0002	100.0	2000	0.5570	29.0550
0.0004	150.0	3000	0.6208	30.6347
0.0	200.0	4000	0.8745	33.5402
0.0	250.0	5000	0.9035	33.0042

Framework versions

• Transformers 4.26.1
• Pytorch 1.11.0+cu102
• Datasets 2.10.0
• Tokenizers 0.13.2