Hugging Face's logo

csikasote
/
xls-r-1b-bem-fsv

Automatic Speech Recognition
TensorBoard
Safetensors
wav2vec2
BembaSpeech
Generated from Trainer
Model card Files Metrics Community
xls-r-1b-bem-fsv / README.md
csikasote's picture
csikasote
End of training
0938039 verified
preview code
|
raw
history blame
No virus
1.83 kB
metadata
license: apache-2.0
base_model: facebook/wav2vec2-xls-r-1b
tags:
  - automatic-speech-recognition
  - BembaSpeech
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: xls-r-1b-bem-fsv
    results: []

Visualize in Weights & Biases

xls-r-1b-bem-fsv

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

  • Loss: 0.2680
  • Wer: 0.8798

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: 5e-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: 500
  • num_epochs: 5.0
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
2.6967 1.9194 500 0.4790 0.9860
0.1815 3.8388 1000 0.2680 0.8798

Framework versions

  • Transformers 4.43.0
  • Pytorch 2.3.1+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1