Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
whisper-tiny-javanese-openslr-v2 – AI Model by bagasshw | AlphaNeural AI
You can deploy this model and start earning money today!
bagasshw
/
whisper-tiny-javanese-openslr-v2
like
0
transformers
tensorboard
safetensors
whisper
automatic-speech-recognition
javanese
asr
generated_from_trainer
jv
jv_id_asr_split
openai/whisper-tiny
finetune
apache-2.0
model-index
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Whisper Tiny Java
This model is a fine-tuned version of
openai/whisper-tiny
on the jv_id_asr_split dataset. It achieves the following results on the evaluation set:
Loss: 0.2792
Wer: 0.6472
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: 2e-05
train_batch_size: 64
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 256
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: linear
lr_scheduler_warmup_ratio: 0.1
training_steps: 2500
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Wer
0.528
0.8643
500
0.4467
0.4770
0.3702
1.7277
1000
0.3424
0.5528
0.2988
2.5946
1500
0.3031
0.5552
0.2607
3.4581
2000
0.2859
0.6485
0.2481
4.3215
2500
0.2792
0.6472
Framework versions
Transformers 4.50.0.dev0
Pytorch 2.6.0+cu126
Datasets 3.4.0
Tokenizers 0.21.1
