Edit model card

wav2vec2-large-xls-r-300m-hindi-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:

  • Loss: 7.2810
  • 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: 0.0003
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 5
  • num_epochs: 5
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
23.4144 0.8 4 29.5895 1.0
19.1336 1.6 8 18.3354 1.0
12.1562 2.4 12 11.2065 1.0
8.1523 3.2 16 8.8674 1.0
6.807 4.0 20 7.8106 1.0
6.1583 4.8 24 7.2810 1.0

Framework versions

  • Transformers 4.11.3
  • Pytorch 1.10.0+cu111
  • Datasets 1.18.3
  • Tokenizers 0.10.3
Downloads last month
1
Inference API
or
This model can be loaded on Inference API (serverless).

Dataset used to train chaitanya97/wav2vec2-large-xls-r-300m-hindi-colab