Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
whispertiny_buah25sil_v1_7 – AI Model by albertuspekerti | AlphaNeural AI
You can deploy this model and start earning money today!
albertuspekerti
/
whispertiny_buah25sil_v1_7
like
0
tensorboard
safetensors
whisper
generated_from_trainer
openai/whisper-tiny
finetune
apache-2.0
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
whispertiny_buah25sil_v1_7
This model is a fine-tuned version of
openai/whisper-tiny
on the None dataset. It achieves the following results on the evaluation set:
Loss: 0.0712
Wer: 5.8764
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: 16
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 5000
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Wer
0.0381
0.2286
1000
0.0855
8.9938
0.0176
0.4571
2000
0.0540
5.7127
0.0211
0.6857
3000
0.0669
6.2349
0.0105
0.9143
4000
0.0666
5.8140
0.0071
1.1429
5000
0.0712
5.8764
Framework versions
Transformers 4.41.2
Pytorch 2.3.0+cu121
Datasets 4.0.0
Tokenizers 0.19.1
