wav2vec2-large-xlsr-moroccan-darija-v4/README.md

license, base_model, tags, metrics, model-index

license	base_model	tags	metrics	model-index
apache-2.0	hassanaitnacer/wav2vec2-large-xlsr-moroccan-darija-v3	generated_from_trainer	wer	name results wav2vec2-large-xlsr-moroccan-darija-v4

wav2vec2-large-xlsr-moroccan-darija-v4

This model is a fine-tuned version of hassanaitnacer/wav2vec2-large-xlsr-moroccan-darija-v3 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0394
• Wer: 0.0816

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: 0.0001
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0512	1.0225	500	0.0410	0.0872
0.0629	2.0450	1000	0.0508	0.0844
0.0384	3.0675	1500	0.0394	0.0816

Framework versions

• Transformers 4.43.0.dev0
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1