metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - fleurs
metrics:
  - wer
model-index:
  - name: facebook/wav2vec2-xls-r-1b
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: fleurs
          type: fleurs
          config: ps_af
          split: test
          args: ps_af
        metrics:
          - name: Wer
            type: wer
            value: 0.9322987721691678

facebook/wav2vec2-xls-r-1b

This model is a fine-tuned version of facebook/wav2vec2-xls-r-1b on the fleurs dataset. It achieves the following results on the evaluation set:

Loss: 4.9040
Wer: 0.9323
Cer: 0.9546

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: 7.5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
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: 1000
training_steps: 500
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Cer	Validation Loss	Wer
19.9558	1.27	100	3.2660	20.9197	1.0
19.7186	2.53	200	1.1692	19.2447	1.0
15.203	3.8	300	15.0053	0.9998	0.9687
6.4303	5.06	400	6.5437	0.9632	0.9911
4.5712	6.33	500	4.9040	0.9323	0.9546

Framework versions

Transformers 4.26.0.dev0
Pytorch 1.13.1+cu117
Datasets 2.7.1.dev0
Tokenizers 0.13.2