Nepali-w2v-bert-2.0 – AI Model by dhasmana | AlphaNeural AI

You can deploy this model and start earning money today!

dhasmana/
Nepali-w2v-bert-2.0

like

0

automatic-speech-recognition

generated_from_trainer

facebook/w2v-bert-2.0

endpoints_compatible

Views

No views yet

Nepali-w2v-bert-2.0

This model is a fine-tuned version of facebook/w2v-bert-2.0 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.3965
Cer: 0.0806

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: 5e-05
train_batch_size: 16
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
1.9958	1.5707	300	0.4762	0.1093
0.3979	3.1414	600	0.4182	0.0995
0.2977	4.7120	900	0.3919	0.0945
0.2301	6.2827	1200	0.3824	0.0865
0.1741	7.8534	1500	0.3733	0.0816
0.1217	9.4241	1800	0.3965	0.0806

Framework versions

Transformers 4.57.6
Pytorch 2.9.0+cu126
Datasets 4.0.0
Tokenizers 0.22.2