README.md

metadata

license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
  - generated_from_trainer
datasets:
  - common_voice_11_0
metrics:
  - wer
model-index:
  - name: wav2vec2-large-xls-r-300m-cv-11-ug-test_01
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: common_voice_11_0
          type: common_voice_11_0
          config: ug
          split: test
          args: ug
        metrics:
          - name: Wer
            type: wer
            value: 1

wav2vec2-large-xls-r-300m-cv-11-ug-test_01

This model is a fine-tuned version of facebook/wav2vec2-base on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:

• Loss: 3.0973
• 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: 0.0001
• 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: 1000
• num_epochs: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
4.9981	8.0	500	3.0973	1.0

Framework versions

• Transformers 4.35.0
• Pytorch 2.0.0
• Datasets 2.14.6
• Tokenizers 0.14.1