wav2vec2-large-xlsr-es-col-pro

This model is a fine-tuned version of jonatasgrosman/wav2vec2-large-xlsr-53-spanish on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0636
• Wer: 0.0507

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: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1032	7.4	400	0.0618	0.0656
0.0687	14.81	800	0.0670	0.0619
0.0402	22.22	1200	0.0693	0.0573
0.0252	29.62	1600	0.0636	0.0507

Framework versions

• Transformers 4.11.3
• Pytorch 1.10.1+cu102
• Datasets 1.13.3
• Tokenizers 0.10.3