Hugging Face's logo

unza
/
xls-r-300m-nyanja-fullset

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
NyanjaSpeech
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
xls-r-300m-nyanja-fullset / README.md
unza's picture
unza
update model card README.md
bcf129c
preview code
|
raw
history blame contribute delete
1.54 kB
metadata
license: apache-2.0
tags:
  - automatic-speech-recognition
  - NyanjaSpeech
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: xls-r-300m-nyanja-fullset
    results: []

xls-r-300m-nyanja-fullset

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the NYANJASPEECH - NYA dataset. It achieves the following results on the evaluation set:

  • Loss: 3.1987
  • 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: 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: 1500
  • num_epochs: 2.0
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
3.3815 1.58 500 3.1987 1.0

Framework versions

  • Transformers 4.25.0.dev0
  • Pytorch 1.12.1+cu113
  • Datasets 2.7.1
  • Tokenizers 0.13.2