Viraj008/whisper-small-mr_v6

Whisper Small MR v6 - Viraj Patil

This model is a fine-tuned version of Viraj008/whisper-small-mr_v5 on the Common Voice 17.0, google/fleurs dataset. It achieves the following results on the evaluation set:

• Loss: 0.2922
• Wer: 34.3775

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
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0307	0.5355	1000	0.2790	36.9235
0.0137	1.0710	2000	0.3011	35.4572
0.015	1.6064	3000	0.2903	35.0240
0.0067	2.1419	4000	0.2922	34.3775

Framework versions

• Transformers 4.45.1
• Pytorch 2.4.0
• Datasets 3.0.1
• Tokenizers 0.20.0