Wav2vec2 Xlsr 1b Ru

🚀 XLS-R 1B Wav2Vec2 Russian by Rasmus Toivanen

This model is a fine - tuned version of facebook/wav2vec2-xls-r-1b on the common_voice dataset. It's designed for automatic speech recognition tasks, offering a solution for converting spoken language into text in Russian.

📦 Installation

No installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

No code examples are provided in the original document, so this section is skipped.

📚 Documentation

Model Details

Model Performance

The model achieves the following results on different evaluation sets:

• Common Voice 8:
  • Test WER: 10.83
  • Test CER: 2.41
• Robust Speech Event - Dev Data:
  • Test WER: 37.71
  • Test CER: 12.98
• Robust Speech Event - Test Data:
  • Test WER: 31.89

Evaluation Results

On the evaluation set, the model achieves the following results:

• Loss: 0.1352
• Wer: 0.0971

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: 32
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 10
• mixed_precision_training: Native AMP

Training Results

Framework Versions

• Transformers 4.17.0.dev0
• Pytorch 1.10.2+cu102
• Datasets 1.18.3
• Tokenizers 0.11.0

🔧 Technical Details

No detailed technical implementation information is provided in the original document, so this section is skipped.

📄 License

No license information is provided in the original document, so this section is skipped.