EzraWilliam's picture
Upload tokenizer
06f85b7 verified
|
raw
history blame
2.49 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
base_model: facebook/wav2vec2-large-xlsr-53
datasets:
  - common_voice_13_0
metrics:
  - wer
model-index:
  - name: wav2vec2-xlsr-53-CV-demo-google-colab-Ezra_William_Prod18
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: common_voice_13_0
          type: common_voice_13_0
          config: id
          split: test
          args: id
        metrics:
          - type: wer
            value: 0.3394174041297935
            name: Wer

wav2vec2-xlsr-53-CV-demo-google-colab-Ezra_William_Prod18

This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the common_voice_13_0 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3716
  • Wer: 0.3394

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: 0.0001
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 12
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
2.8966 1.0 278 2.7818 1.0
0.7308 2.0 556 0.5667 0.5799
0.4205 3.0 834 0.3971 0.4407
0.3017 4.0 1112 0.3938 0.4124
0.2371 5.0 1390 0.3519 0.3909
0.1977 6.0 1668 0.3638 0.3797
0.1631 7.0 1946 0.3623 0.3773
0.1445 8.0 2224 0.3490 0.3654
0.1329 9.0 2502 0.3658 0.3509
0.1162 10.0 2780 0.3683 0.3477
0.109 11.0 3058 0.3728 0.3410
0.0999 12.0 3336 0.3716 0.3394

Framework versions

  • Transformers 4.40.1
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.0
  • Tokenizers 0.19.1