Modelpublic

aldiiii-mln/wav2vec2-mms-bugis-synthetic-only

sourceHugging Faceupdated 3mo agoView on Hugging Face

0likes6downloads

Model Card

wav2vec2-mms-bugis-synthetic-only

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

—Loss: 0.2906
—Wer: 0.3714

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: 0.001
—trainbatchsize: 8
—evalbatchsize: 8
—seed: 42
—optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
—lrschedulertype: linear
—lrschedulerwarmup_steps: 50
—num_epochs: 15
—mixedprecisiontraining: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
4.7478	1.0	41	4.5729	1.0
3.3476	2.0	82	2.9451	1.0
1.0053	3.0	123	0.8956	0.6848
0.6516	4.0	164	0.7000	0.5672
0.5947	5.0	205	0.6306	0.5434
0.5120	6.0	246	0.5929	0.4944
0.4544	7.0	287	0.6089	0.4778
0.4740	8.0	328	0.5729	0.4672
0.4074	9.0	369	0.5674	0.4667
0.4247	10.0	410	0.5748	0.4646
0.4036	11.0	451	0.5519	0.4444
0.3406	12.0	492	0.5638	0.4364
0.4277	13.0	533	0.5573	0.4414
0.3966	14.0	574	0.5556	0.4348
0.3747	15.0	615	0.5551	0.4379

Framework versions

—Transformers 5.13.0.dev0
—Pytorch 2.11.0+cu128
—Datasets 4.0.0
—Tokenizers 0.22.2