Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
whisper-bn – AI Model by lucius-40 | AlphaNeural AI
You can deploy this model and start earning money today!
lucius-40
/
whisper-bn
like
0
transformers
tensorboard
safetensors
whisper
automatic-speech-recognition
generated_from_trainer
bangla-speech-processing/BanglaASR
finetune
mit
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
whisper-bn
This model is a fine-tuned version of
bangla-speech-processing/BanglaASR
on the None dataset. It achieves the following results on the evaluation set:
eval_loss: 0.0709
eval_wer: 24.0044
eval_levenshtein_similarity: 0.8521
eval_runtime: 153.8315
eval_samples_per_second: 2.178
eval_steps_per_second: 0.273
epoch: 7.0
step: 2639
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: 8
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
num_epochs: 10
mixed_precision_training: Native AMP
Framework versions
Transformers 4.48.3
Pytorch 2.6.0+cu124
Datasets 3.6.0
Tokenizers 0.21.2
