Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
whisper-large-59A – AI Model by facuvillegas | AlphaNeural AI
You can deploy this model and start earning money today!
facuvillegas
/
whisper-large-59A
like
0
transformers
tensorboard
safetensors
whisper
automatic-speech-recognition
generated_from_trainer
openai/whisper-large-v3-turbo
finetune
mit
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
whisper-large-59A
This model is a fine-tuned version of
openai/whisper-large-v3-turbo
on the None dataset. It achieves the following results on the evaluation set:
Loss: 0.2250
Wer: 10.6061
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: 6000
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Wer
0.0
250.0
1000
0.2091
12.1212
0.0
500.0
2000
0.2172
12.1212
0.0
750.0
3000
0.2198
10.6061
0.0
1000.0
4000
0.2232
10.6061
0.0
1250.0
5000
0.2251
10.6061
0.0
1500.0
6000
0.2250
10.6061
Framework versions
Transformers 4.49.0
Pytorch 2.6.0+cu124
Datasets 3.4.1
Tokenizers 0.21.1
