Edit model card

wav2vec2-large-xls-r-1B-common_voice7-lt-ft

This model is a fine-tuned version of facebook/wav2vec2-xls-r-1b on the common_voice dataset. It achieves the following results on the evaluation set:

  • Loss: 2.5101
  • Wer: 1.0

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: 3e-05
  • train_batch_size: 36
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 72
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 900
  • num_epochs: 100
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
2.3491 31.24 500 3.9827 1.0
0.0421 62.48 1000 2.9544 1.0
0.0163 93.73 1500 2.5101 1.0

Framework versions

  • Transformers 4.16.0.dev0
  • Pytorch 1.10.1+cu102
  • Datasets 1.17.1.dev0
  • Tokenizers 0.10.3
Downloads last month
1
Hosted inference API
or or
This model can be loaded on the Inference API on-demand.

Dataset used to train reach-vb/wav2vec2-large-xls-r-1B-common_voice7-lt-ft