Hugging Face's logo

susmitabhatt
/
xlsr-big-knnn

TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Model card Files Metrics Community
xlsr-big-knnn / README.md
susmitabhatt's picture
susmitabhatt
End of training
16acafe verified
preview code
|
raw
history blame
No virus
1.51 kB
metadata
license: apache-2.0
base_model: facebook/wav2vec2-large-xlsr-53
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: xlsr-big-knnn
    results: []

xlsr-big-knnn

This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.7119
  • Wer: 0.9924

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: 0.0004
  • 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: 132
  • num_epochs: 2
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
2.7762 1.0753 100 1.7119 0.9924

Framework versions

  • Transformers 4.45.0.dev0
  • Pytorch 2.1.2
  • Datasets 2.20.1.dev0
  • Tokenizers 0.19.1