README.md

metadata

library_name: transformers
license: apache-2.0
base_model: jonatasgrosman/wav2vec2-large-xlsr-53-russian
tags:
  - generated_from_trainer
datasets:
  - common_voice_17_0
metrics:
  - wer
model-index:
  - name: wav2vec2-russian
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: common_voice_17_0
          type: common_voice_17_0
          config: ru
          split: None
          args: ru
        metrics:
          - name: Wer
            type: wer
            value: 32.86787139169209

wav2vec2-russian

This model is a fine-tuned version of jonatasgrosman/wav2vec2-large-xlsr-53-russian on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2723
• Wer: 32.8679

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
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2061	1.2780	400	0.2723	32.8679

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.6.0
• Tokenizers 0.21.0