Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
whisper-tiny-id-puct-4k – AI Model by CheeLi03 | AlphaNeural AI
You can deploy this model and start earning money today!
CheeLi03
/
whisper-tiny-id-puct-4k
like
0
transformers
tensorboard
safetensors
whisper
automatic-speech-recognition
hf-asr-leaderboard
generated_from_trainer
id
fleurs
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 Indonesian - Chee Li
This model is a fine-tuned version of
openai/whisper-tiny
on the Google Fleurs dataset. It achieves the following results on the evaluation set:
Loss: 0.7988
Wer: 45.4151
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: Use 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_steps: 500
training_steps: 4000
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Wer
0.1718
5.4348
1000
0.6667
52.1167
0.0263
10.8696
2000
0.7266
46.9035
0.007
16.3043
3000
0.7828
43.6799
0.0053
21.7391
4000
0.7988
45.4151
Framework versions
Transformers 4.46.2
Pytorch 2.3.1+cu121
Datasets 2.20.0
Tokenizers 0.20.1
