Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
whisper-medium-singleword – AI Model by WayneTK | AlphaNeural AI
You can deploy this model and start earning money today!
WayneTK
/
whisper-medium-singleword
like
0
transformers
tensorboard
safetensors
whisper
automatic-speech-recognition
generated_from_trainer
en
CGE
openai/whisper-medium
finetune
apache-2.0
model-index
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Whisper Medium SingleWord
This model is a fine-tuned version of
openai/whisper-medium
on the CGE-Pronounce dataset. It achieves the following results on the evaluation set:
Loss: 0.1796
Wer: 18.7586
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 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_steps: 500
training_steps: 4000
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Wer
0.1618
0.9158
1000
0.1910
23.7288
0.082
1.8315
2000
0.1800
19.9954
0.0267
2.7473
3000
0.1775
19.3083
0.0074
3.6630
4000
0.1796
18.7586
Framework versions
Transformers 4.51.3
Pytorch 2.6.0+cu124
Datasets 3.6.0
Tokenizers 0.21.1
