xls-r-300m-es / README.md
polodealvarado's picture
Update README.md
c260866
|
raw
history blame
2.65 kB
metadata
license: apache-2.0
language:
  - es
tags:
  - generated_from_trainer
  - robust-speech-event
  - common_voice_8_0
  - mozilla-foundation/common_voice_8_0
datasets:
  - mozilla-foundation/common_voice_8_0
model-index:
  - name: wave2vec-xls-r-300m-es
    results:
      - task:
          name: Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: mozilla-foundation/common_voice_8_0 es
          type: mozilla-foundation/common_voice_8_0
          args: es
        metrics:
          - name: Test WER
            type: wer
            value: 14.38

xls-r-300m-es with n-gram(5)

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 (Test): 0.1900
  • Wer (Test): 0.1438

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: 4
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
3.6747 0.3 400 0.6535 0.5926
0.4439 0.6 800 0.3753 0.3193
0.3291 0.9 1200 0.3267 0.2721
0.2644 1.2 1600 0.2816 0.2311
0.24 1.5 2000 0.2647 0.2179
0.2265 1.79 2400 0.2406 0.2048
0.1994 2.09 2800 0.2357 0.1869
0.1613 2.39 3200 0.2242 0.1821
0.1546 2.69 3600 0.2123 0.1707
0.1441 2.99 4000 0.2067 0.1619
0.1138 3.29 4400 0.2044 0.1519
0.1072 3.59 4800 0.1917 0.1457
0.0992 3.89 5200 0.1900 0.1438

Framework versions

  • Transformers 4.16.0.dev0
  • Pytorch 1.10.1+cu102
  • Datasets 1.17.1.dev0
  • Tokenizers 0.11.0