simpragma/breeze-dsw-base-ml

Breeze DSW Malayalam - base

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

• Loss: 0.6260
• Wer: 42.7247

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: 2000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.3151	4.02	200	0.4517	54.5134
0.0703	9.02	400	0.4561	46.7285
0.0144	14.02	600	0.5625	43.7627
0.006	19.02	800	0.6260	42.7247
0.0024	24.02	1000	0.6938	43.0306
0.0012	29.02	1200	0.7354	44.2169

Framework versions

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