You can deploy this model and start earning money today!

tettoewai/
whisper-burmese-myanify

Name: whisper-burmese-myanify
Availability: InStock

automatic-speech-recognition

generated_from_trainer

tettoewai/whisper-burmese-myanify

finetune

endpoints_compatible

Views

No views yet

whisper-burmese-myanify

This model is a fine-tuned version of tettoewai/whisper-burmese-myanify on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.3599
Cer: 0.5358

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: 4
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 200
training_steps: 3000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
0.0138	1.4292	500	0.3152	0.5438
0.0096	2.8584	1000	0.3197	0.5498
0.0036	4.2861	1500	0.3336	0.5401
0.0018	5.7153	2000	0.3527	0.5378
0.0002	7.1431	2500	0.3569	0.5362
0.0001	8.5722	3000	0.3599	0.5358

Framework versions

Transformers 5.10.2
Pytorch 2.11.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2