Hugging Face's logo

rebeccaforeflight
/
finetuned_Wav2Vec2_on_ATCOSIM

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
finetuned_Wav2Vec2_on_ATCOSIM / README.md
Rebecca Iglesias-Flores
End of training
1f5751e
preview code
|
raw
history blame
2.16 kB
metadata
license: apache-2.0
base_model: facebook/wav2vec2-xls-r-300m
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: finetuned_Wav2Vec2_on_ATCOSIM
    results: []

finetuned_Wav2Vec2_on_ATCOSIM

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

  • Loss: 0.1707
  • Wer: 0.1170

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: 5
  • total_train_batch_size: 40
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 30

Training results

Training Loss Epoch Step Validation Loss Wer
2.6927 2.5 400 0.5557 0.4100
0.3288 4.99 800 0.2382 0.1943
0.1856 7.49 1200 0.1957 0.1699
0.1325 9.99 1600 0.1845 0.1572
0.1018 12.48 2000 0.1771 0.1534
0.0899 14.98 2400 0.1637 0.1356
0.0722 17.48 2800 0.1812 0.1409
0.0596 19.98 3200 0.1747 0.1323
0.046 22.47 3600 0.1505 0.1307
0.037 24.97 4000 0.1705 0.1224
0.0294 27.47 4400 0.1614 0.1164
0.0249 29.96 4800 0.1707 0.1170

Framework versions

  • Transformers 4.34.0.dev0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.13.3