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
52a97a4 verified
preview code
|
raw
history blame
3.23 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: 0.4349
  • Wer: 0.3391

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: 16
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 32
  • 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 0.0774 100 3.5346 1.0
No log 0.1549 200 2.9829 1.0
No log 0.2323 300 2.7705 1.0
No log 0.3097 400 1.3696 0.8535
3.7305 0.3871 500 1.0936 0.7465
3.7305 0.4646 600 0.8457 0.6413
3.7305 0.5420 700 0.7860 0.5836
3.7305 0.6194 800 0.7366 0.5637
3.7305 0.6969 900 0.7319 0.5494
0.7504 0.7743 1000 0.6439 0.5104
0.7504 0.8517 1100 0.6214 0.4759
0.7504 0.9292 1200 0.5957 0.4628
0.7504 1.0066 1300 0.5717 0.4353
0.7504 1.0840 1400 0.5500 0.4192
0.5571 1.1614 1500 0.5342 0.4073
0.5571 1.2389 1600 0.5207 0.4024
0.5571 1.3163 1700 0.5142 0.3969
0.5571 1.3937 1800 0.5083 0.3958
0.5571 1.4712 1900 0.4886 0.3825
0.4603 1.5486 2000 0.4733 0.3743
0.4603 1.6260 2100 0.4616 0.3619
0.4603 1.7034 2200 0.4536 0.3627
0.4603 1.7809 2300 0.4488 0.3487
0.4603 1.8583 2400 0.4429 0.3481
0.4163 1.9357 2500 0.4377 0.3419
0.4163 2.0132 2600 0.4349 0.3391

Framework versions

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