anuragshas/whisper-small-pa

Whisper Small Punjabi

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

• Loss: 0.5991
• Wer: 39.0469

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: 64
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 400
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.4346	5.01	50	0.3902	49.6797
0.0728	11.0	100	0.3811	40.7379
0.009	16.02	150	0.4924	39.5081
0.0028	22.0	200	0.5309	38.7394
0.0008	27.02	250	0.5687	38.6369
0.0006	33.01	300	0.5859	39.0213
0.0005	38.02	350	0.5954	39.0981
0.0005	44.01	400	0.5991	39.0469

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.13.0+cu117
• Datasets 2.7.1.dev0
• Tokenizers 0.13.2