wav2vec2-xls-r-300m-runyankole-asr-model-yogera-dataset

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on an unknown dataset. It achieves the following results on the evaluation set:

• eval_loss: 1.5019
• eval_wer: 0.5605
• eval_cer: 0.1716
• eval_runtime: 30.2724
• eval_samples_per_second: 18.895
• eval_steps_per_second: 1.189
• epoch: 40.0
• step: 2860

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: 32
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• 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: cosine
• lr_scheduler_warmup_ratio: 0.05
• num_epochs: 50

Framework versions

• Transformers 4.46.1
• Pytorch 2.8.0.dev20250319+cu128
• Datasets 3.2.0
• Tokenizers 0.20.3