wav2vec2-large-xls-r-300m-gn-it-colab

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: 0.9405
• Wer: 0.6307

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• 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: 500
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
6.2799	3.23	400	3.1016	0.9996
1.2437	6.45	800	1.0110	0.8547
0.3811	9.68	1200	0.9178	0.7471
0.2215	12.9	1600	0.9287	0.7458
0.1554	16.13	2000	0.9884	0.7148
0.1203	19.35	2400	0.9579	0.6854
0.0937	22.58	2800	0.9581	0.6642
0.074	25.81	3200	0.9350	0.6384
0.0583	29.03	3600	0.9419	0.6331

Framework versions

• Transformers 4.34.1
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1