simpragma/breeze-listen-dsw-base-hi

Breeze DSW Hindi - base

This model is a fine-tuned version of openai/whisper-base on the mozilla-foundation/common_voice_16_0 hi dataset. It achieves the following results on the evaluation set:

• Loss: 0.5205
• Wer: 28.5029

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: 16
• seed: 42
• distributed_type: multi-GPU
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.553	0.1	100	0.6445	39.4988
0.3683	1.08	200	0.5342	33.0660
0.2855	2.07	300	0.4983	31.4251
0.2233	3.06	400	0.4868	30.1547
0.1832	4.04	500	0.4783	28.9540
0.1431	5.03	600	0.4902	29.1828
0.0972	6.01	700	0.5049	28.6380
0.0715	6.11	800	0.5205	28.5029
0.0579	7.09	900	0.5366	28.9475
0.0519	8.08	1000	0.5381	28.7949

Framework versions

• Transformers 4.37.0.dev0
• Pytorch 2.1.2+cu121
• Datasets 2.16.2.dev0
• Tokenizers 0.15.0