Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
hubert-naija-asr-ft – AI Model by Tobi-Shalom | AlphaNeural AI
You can deploy this model and start earning money today!
Tobi-Shalom
/
hubert-naija-asr-ft
like
0
transformers
safetensors
hubert
automatic-speech-recognition
generated_from_trainer
facebook/hubert-large-ls960-ft
finetune
apache-2.0
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
hubert-naija-asr-ft
This model is a fine-tuned version of
facebook/hubert-large-ls960-ft
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 1.0578
Wer: 1.9785
Cer: 0.3892
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: 0.0002
train_batch_size: 16
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
gradient_accumulation_steps: 2
total_train_batch_size: 32
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
num_epochs: 15.0
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Wer
Cer
No log
3.3915
400
0.9210
1.9809
0.4430
3.5907
6.7830
800
0.8104
1.9785
0.4143
0.654
10.1702
1200
0.8962
1.9761
0.3918
0.321
13.5617
1600
1.0578
1.9785
0.3892
Framework versions
Transformers 4.53.0.dev0
Pytorch 2.7.1+cu126
Datasets 3.6.0
Tokenizers 0.21.1
