sitwala/whisper-large-v3-turbo-nchlt-ven

Whisper whisper-large-v3-turbo nchlt

This model is a fine-tuned version of openai/whisper-large-v3-turbo on the dsfsi/multilingual-nchlt-dataset dataset. It achieves the following results on the evaluation set:

• Loss: 0.1575
• Wer: 10.8532

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: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: constant_with_warmup
• lr_scheduler_warmup_steps: 200
• training_steps: 2000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2009	0.125	250	0.2447	18.5502
0.2014	1.0075	500	0.2246	17.0841
0.1023	1.1325	750	0.1829	14.2435
0.0985	2.015	1000	0.1690	12.4516
0.0989	2.14	1250	0.1816	14.3352
0.0576	3.0225	1500	0.1622	11.8713
0.0838	3.1475	1750	0.1744	14.7424
0.0408	4.03	2000	0.1575	10.8532

Framework versions

• Transformers 4.52.0
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.4