wdecay-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:

• eval_loss: 0.4938
• eval_wer: 0.3092
• eval_cer: 0.0969
• eval_runtime: 337.3416
• eval_samples_per_second: 14.638
• eval_steps_per_second: 1.832
• epoch: 14.87
• step: 4000

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
• 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: 40
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.18.0
• Pytorch 1.11.0+cu113
• Datasets 1.18.3
• Tokenizers 0.12.1