Hugging Face's logo

DewiBrynJones
/
wav2vec2-xlsr-53-ft-btb-ccv-cy

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
wav2vec2-xlsr-53-ft-btb-ccv-cy / README.md
DewiBrynJones's picture
DewiBrynJones
End of training
ce354d9 verified
preview code
|
raw
history blame
3.41 kB
metadata
license: apache-2.0
base_model: facebook/wav2vec2-large-xlsr-53
tags:
  - automatic-speech-recognition
  - DewiBrynJones/banc-trawsgrifiadau-bangor-clean-with-ccv
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: wav2vec2-xlsr-53-ft-btb-ccv-cy
    results: []

wav2vec2-xlsr-53-ft-btb-ccv-cy

This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the DEWIBRYNJONES/BANC-TRAWSGRIFIADAU-BANGOR-CLEAN-WITH-CCV - DEFAULT dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5355
  • Wer: 0.4186

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
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • training_steps: 3000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
No log 0.0194 100 3.5494 1.0
No log 0.0387 200 3.0426 1.0
No log 0.0581 300 2.8965 1.0
No log 0.0774 400 1.8263 0.9829
3.9715 0.0968 500 1.3860 0.8749
3.9715 0.1161 600 1.3084 0.8153
3.9715 0.1355 700 1.0550 0.7337
3.9715 0.1549 800 1.0012 0.7190
3.9715 0.1742 900 0.9137 0.6752
1.0155 0.1936 1000 0.8486 0.6469
1.0155 0.2129 1100 0.8535 0.6112
1.0155 0.2323 1200 0.8350 0.6193
1.0155 0.2516 1300 0.7681 0.5670
1.0155 0.2710 1400 0.7377 0.5559
0.7987 0.2904 1500 0.7130 0.5437
0.7987 0.3097 1600 0.7040 0.5452
0.7987 0.3291 1700 0.6729 0.5051
0.7987 0.3484 1800 0.6646 0.5113
0.7987 0.3678 1900 0.6531 0.4969
0.6851 0.3871 2000 0.6414 0.5038
0.6851 0.4065 2100 0.6109 0.4677
0.6851 0.4259 2200 0.6035 0.4692
0.6851 0.4452 2300 0.5802 0.4590
0.6851 0.4646 2400 0.5720 0.4455
0.5979 0.4839 2500 0.5695 0.4426
0.5979 0.5033 2600 0.5557 0.4351
0.5979 0.5226 2700 0.5499 0.4270
0.5979 0.5420 2800 0.5451 0.4258
0.5979 0.5614 2900 0.5383 0.4217
0.5753 0.5807 3000 0.5355 0.4186

Framework versions

  • Transformers 4.40.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1