PolyChirag/Marathi_WhisperASR

Whisper Tiny MR - Chirag Brahme

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: 0.7911
• Wer: 69.4410

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: 16
• eval_batch_size: 8
• 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
0.145	4.07	1000	0.4587	66.9138
0.046	8.13	2000	0.5455	68.4804
0.0142	12.2	3000	0.6589	69.0091
0.004	16.26	4000	0.7581	69.4797
0.002	20.33	5000	0.7911	69.4410

Framework versions

• Transformers 4.39.3
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.15.2