wav2vec2-large-xls-r-300m-tsovatush-demo-colab-bryn-hauk-9-21 – AI Model by kkahadze | AlphaNeural AI

You can deploy this model and start earning money today!

kkahadze/
wav2vec2-large-xls-r-300m-tsovatush-demo-colab-bryn-hauk-9-21

like

0

automatic-speech-recognition

generated_from_trainer

facebook/wav2vec2-xls-r-300m

endpoints_compatible

Views

No views yet

wav2vec2-large-xls-r-300m-tsovatush-demo-colab-bryn-hauk-9-21

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: 1.2641
Wer: None
Cer: None

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: 0.0003
train_batch_size: 16
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 50
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
5.3691	5.6338	400	3.5145	None	None
2.3829	11.2676	800	1.1264	None	None
0.8921	16.9014	1200	1.0416	0.5504	0.2172
0.515	22.5352	1600	1.0066	None	None
0.3268	28.1690	2000	1.1589	0.5101	0.1869
0.2142	33.8028	2400	1.2165	0.5144	0.1934
0.1496	39.4366	2800	1.1939	None	None
0.1013	45.0704	3200	1.2641	None	None

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 1.18.3
Tokenizers 0.19.1