Hugging Face's logo

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

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
DewiBrynJones/banc-trawsgrifiadau-bangor-clean-with-ccv
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
d25ceb2 verified
preview code
|
raw
history blame
No virus
3.17 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: 0.4971
  • Wer: 0.3381

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: 64
  • 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: 2600
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
No log 0.1548 100 3.5561 1.0
No log 0.3096 200 3.3712 1.0
No log 0.4644 300 3.1736 1.0
No log 0.6192 400 1.1719 0.7910
3.7217 0.7740 500 0.9169 0.6776
3.7217 0.9288 600 0.8097 0.6191
3.7217 1.0836 700 0.6986 0.5080
3.7217 1.2384 800 0.6123 0.4629
3.7217 1.3932 900 0.5815 0.4499
0.6148 1.5480 1000 0.5666 0.4218
0.6148 1.7028 1100 0.5285 0.4049
0.6148 1.8576 1200 0.5309 0.3972
0.6148 2.0124 1300 0.4993 0.3818
0.6148 2.1672 1400 0.4779 0.3722
0.4634 2.3220 1500 0.4679 0.3659
0.4634 2.4768 1600 0.4679 0.3621
0.4634 2.6316 1700 0.4525 0.3504
0.4634 2.7864 1800 0.4353 0.3357
0.4634 2.9412 1900 0.4358 0.3423
0.3708 3.0960 2000 0.4391 0.3355
0.3708 3.2508 2100 0.4307 0.3282
0.3708 3.4056 2200 0.4274 0.3275
0.3708 3.5604 2300 0.4388 0.3246
0.3708 3.7152 2400 0.4521 0.3277
0.3391 3.8700 2500 0.4861 0.3390
0.3391 4.0248 2600 0.4971 0.3381

Framework versions

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