Hugging Face's logo

NbAiLab
/
xls-npsc

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
NbAiLab/NPSC
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
xls-npsc / README.md
versae's picture
versae
update model card README.md
ac1100c
preview code
|
raw
history blame
1.35 kB
metadata
license: apache-2.0
tags:
  - automatic-speech-recognition
  - NbAiLab/NPSC
  - generated_from_trainer
datasets:
  - npsc
model-index:
  - name: xls-npsc
    results: []

xls-npsc

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the NBAILAB/NPSC - 48K_MP3 dataset. It achieves the following results on the evaluation set:

  • Loss: 3.5006
  • 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: 7.5e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 10.0
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • Transformers 4.16.0.dev0
  • Pytorch 1.10.1+cu102
  • Datasets 1.18.1.dev0
  • Tokenizers 0.10.3