xls-r-300m-unpaired – AI Model by duck-hug-567 | AlphaNeural AI

You can deploy this model and start earning money today!

duck-hug-567/
xls-r-300m-unpaired

like

0

automatic-speech-recognition

generated_from_trainer

facebook/wav2vec2-xls-r-300m

endpoints_compatible

Views

No views yet

xls-r-300m-unpaired

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the None dataset. It achieves the following results on the evaluation set:

Loss: inf
Cer: 0.9521

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: 3e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
optimizer: Use 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: 2000
num_epochs: 50
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
4.3493	1.0	957	inf	1.0
3.2189	2.0	1914	inf	0.9363
3.3135	3.0	2871	inf	0.9542
3.3114	4.0	3828	inf	0.9522
3.3588	5.0	4785	inf	0.9522
3.3253	6.0	5742	inf	0.9522
3.3732	7.0	6699	inf	0.9521
3.4204	8.0	7656	inf	0.9521

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0