vioannidis's picture
End of training
c4eb41f
|
raw
history blame
2.01 kB
metadata
license: apache-2.0
base_model: facebook/wav2vec2-xls-r-300m
tags:
  - generated_from_trainer
datasets:
  - common_voice
metrics:
  - wer
model-index:
  - name: wav2vec2-large-xls-r-300m-dutch-fast-colab
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: common_voice
          type: common_voice
          config: nl
          split: test
          args: nl
        metrics:
          - name: Wer
            type: wer
            value: 0.37981610317750925

wav2vec2-large-xls-r-300m-dutch-fast-colab

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

  • Loss: 0.5065
  • Wer: 0.3798

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: 300
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss Wer
4.463 0.68 200 2.9358 1.0
1.8336 1.36 400 0.9449 0.6652
0.332 2.03 600 0.6117 0.4496
0.1614 2.71 800 0.5065 0.3798

Framework versions

  • Transformers 4.32.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.4
  • Tokenizers 0.13.3