whitefox123's picture
End of training
7b2cbfa verified
metadata
license: mit
base_model: facebook/w2v-bert-2.0
tags:
  - generated_from_trainer
datasets:
  - audiofolder
metrics:
  - wer
model-index:
  - name: w2v-bert-2.0-arabic-4
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: audiofolder
          type: audiofolder
          config: default
          split: test
          args: default
        metrics:
          - name: Wer
            type: wer
            value: 0.1809009009009009

w2v-bert-2.0-arabic-4

This model is a fine-tuned version of facebook/w2v-bert-2.0 on the audiofolder dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1952
  • Wer: 0.1809

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: 5e-05
  • 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: 2
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
1.5106 0.96 300 0.2448 0.2858
0.2479 1.92 600 0.1952 0.1809

Framework versions

  • Transformers 4.38.0.dev0
  • Pytorch 2.1.0+cu118
  • Datasets 2.17.1
  • Tokenizers 0.15.2