wav2vec2-large-mms-1b-km-kag – AI Model by bqkhanh | AlphaNeural AI

You can deploy this model and start earning money today!

bqkhanh/
wav2vec2-large-mms-1b-km-kag

like

0

generated_from_trainer

facebook/mms-1b-all

Views

No views yet

wav2vec2-large-mms-1b-km-kag

This model is a fine-tuned version of facebook/mms-1b-all on the fleurs dataset. It achieves the following results on the evaluation set:

Loss: 0.7023
Wer: 0.9719

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
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 100
num_epochs: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
8.6022	0.4773	50	7.6316	1.0
4.2957	0.9547	100	1.5845	1.0002
0.4638	1.4320	150	0.7462	0.9896
0.3947	1.9093	200	0.7247	0.9819
0.3653	2.3866	250	0.7122	0.9763
0.375	2.8640	300	0.7079	0.9731
0.3425	3.3413	350	0.7112	0.9707
0.3319	3.8186	400	0.7080	0.9678
0.3336	4.2959	450	0.7023	0.9707
0.3355	4.7733	500	0.7023	0.9719

Framework versions

Transformers 4.41.2
Pytorch 2.8.0+cu126
Datasets 2.21.0
Tokenizers 0.19.1