wav2vec2-librispeech-clean-100h-demo-dist

This model is a fine-tuned version of facebook/wav2vec2-large-lv60 on the LIBRISPEECH_ASR - CLEAN dataset. It achieves the following results on the evaluation set:

• Loss: 0.0554
• Wer: 0.0920

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: 4
• 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: 3.0
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 4.53.1
• Pytorch 2.7.0+cu126
• Datasets 2.21.0
• Tokenizers 0.21.2