mms-TARIC

This model is a fine-tuned version of facebook/mms-1b-all on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.5919
• Wer: 93.5

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: 1e-05
• train_batch_size: 20
• eval_batch_size: 12
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant_with_warmup
• lr_scheduler_warmup_steps: 250
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
4.754	0.7	500	4.3964	100.0
3.1365	1.4	1000	2.9634	99.8333
2.1983	2.1	1500	2.0130	98.75
1.8176	2.81	2000	1.7127	94.75
1.7473	3.51	2500	1.5919	93.5

Framework versions

• Transformers 4.33.2
• Pytorch 2.0.1
• Datasets 2.19.1
• Tokenizers 0.13.3