simran14/marathi-small-whisper-val-8e

simrank14 Whisper Small marathi val 8e

This model is a fine-tuned version of simran14/marathi-small-whisper-train-8e on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3820
• Wer: 17.4462

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: 8
• 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: 100
• num_epochs: 8
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0627	2.3697	500	0.2852	17.7754
0.0099	4.7393	1000	0.3458	17.8499
0.0008	7.1090	1500	0.3820	17.4462

Framework versions

• Transformers 4.43.0.dev0
• Pytorch 2.3.0+cu121
• Datasets 2.20.1.dev0
• Tokenizers 0.19.1