binary-bert-for-sequence-classification – AI Model by tuanio | AlphaNeural AI

You can deploy this model and start earning money today!

tuanio/
binary-bert-for-sequence-classification

like

0

automatic-speech-recognition

generated_from_trainer

facebook/wav2vec2-xls-r-300m

endpoints_compatible

Views

No views yet

1-epochs5-char-based-freeze_cnn-dropout0.1

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.1245
Wer: 0.0865

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: 2e-05
train_batch_size: 10
eval_batch_size: 2
seed: 42
distributed_type: multi-GPU
num_devices: 4
total_train_batch_size: 40
total_eval_batch_size: 8
optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
2.8545	0.37	2500	2.8872	1.0
0.7012	0.74	5000	0.3473	0.2840
0.46	1.11	7500	0.2032	0.1510
0.3848	1.48	10000	0.1668	0.1194
0.3535	1.85	12500	0.1518	0.1086
0.3667	2.22	15000	0.1442	0.1019
0.3058	2.59	17500	0.1381	0.0961
0.3026	2.96	20000	0.1327	0.0924
0.2891	3.33	22500	0.1326	0.0917
0.294	3.7	25000	0.1278	0.0894
0.2846	4.07	27500	0.1257	0.0885
0.259	4.44	30000	0.1244	0.0874
0.2348	4.81	32500	0.1245	0.0865

Framework versions

Transformers 4.34.0
Pytorch 2.0.1
Datasets 2.14.5
Tokenizers 0.14.1