w2v-bert-2.0-test – AI Model by asr-africa | AlphaNeural AI

You can deploy this model and start earning money today!

asr-africa/
w2v-bert-2.0-test

like

0

automatic-speech-recognition

generated_from_trainer

facebook/w2v-bert-2.0

endpoints_compatible

Views

No views yet

w2v-bert-2.0-test

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: 0.2815
Wer: 0.2494
Cer: 0.0627

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 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_ratio: 0.1
num_epochs: 5.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.8172	1.0	1473	0.3534	0.3020	0.0763
0.2395	2.0	2946	0.2995	0.2780	0.0701
0.1948	3.0	4419	0.2876	0.2576	0.0649
0.1665	4.0	5892	0.2886	0.2583	0.0640
0.1462	5.0	7365	0.2815	0.2494	0.0627

Framework versions

Transformers 4.51.3
Pytorch 2.6.0+cu124
Datasets 3.5.0
Tokenizers 0.21.1