README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - common_voice
metrics:
  - wer
model-index:
  - name: wav2vec2-xls-r-300m-de-colab
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: common_voice
          type: common_voice
          config: de
          split: test[:1000]
          args: de
        metrics:
          - name: Wer
            type: wer
            value: 1

wav2vec2-xls-r-300m-de-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: 15.7062
• 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: 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: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
13.8115	0.43	10	15.7936	1.0
14.2706	0.87	20	15.7062	1.0

Framework versions

• Transformers 4.28.1
• Pytorch 1.13.1+cpu
• Datasets 2.11.0
• Tokenizers 0.13.3