jcrkn's picture
End of training
eb73f64
metadata
license: apache-2.0
base_model: facebook/wav2vec2-xls-r-300m
tags:
  - generated_from_trainer
datasets:
  - common_voice_13_0
metrics:
  - wer
model-index:
  - name: wav2vec2-large-xls-r-300m-breton-colab_lr
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: common_voice_13_0
          type: common_voice_13_0
          config: br
          split: test
          args: br
        metrics:
          - name: Wer
            type: wer
            value: 1

wav2vec2-large-xls-r-300m-breton-colab_lr

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice_13_0 dataset. It achieves the following results on the evaluation set:

  • Loss: 3.3053
  • Wer: 1.0

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: 3e-05
  • 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: 5

Training results

Training Loss Epoch Step Validation Loss Wer
14.0739 0.67 200 7.9939 1.0
4.5637 1.34 400 3.9380 1.0
3.2975 2.02 600 3.1902 1.0
3.0457 2.69 800 3.1215 1.0
2.8262 3.36 1000 3.1005 1.0
2.2082 4.03 1200 3.2135 1.0
1.7804 4.71 1400 3.3053 1.0

Framework versions

  • Transformers 4.32.1
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.4
  • Tokenizers 0.13.3