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
fe8fd2a verified
preview code
|
raw
history blame
7.78 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: 2.8074
  • Wer: 0.9983

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: 1000
  • training_steps: 10000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
No log 0.0566 100 4.1582 1.0
No log 0.1133 200 3.1276 1.0
No log 0.1699 300 3.4072 1.0
No log 0.2265 400 2.1967 0.9899
4.6703 0.2831 500 1.0576 0.7174
4.6703 0.3398 600 0.8877 0.6405
4.6703 0.3964 700 0.7894 0.5861
4.6703 0.4530 800 0.7699 0.5877
4.6703 0.5096 900 0.7605 0.5403
0.5242 0.5663 1000 0.7429 0.5495
0.5242 0.6229 1100 0.6762 0.5081
0.5242 0.6795 1200 0.6703 0.5072
0.5242 0.7361 1300 0.6187 0.4623
0.5242 0.7928 1400 0.6205 0.4742
0.4093 0.8494 1500 0.6089 0.4607
0.4093 0.9060 1600 0.6079 0.4564
0.4093 0.9626 1700 0.5752 0.4487
0.4093 1.0193 1800 0.5519 0.4174
0.4093 1.0759 1900 0.5468 0.4107
0.3366 1.1325 2000 0.5372 0.4080
0.3366 1.1891 2100 0.5359 0.4072
0.3366 1.2458 2200 0.5304 0.4023
0.3366 1.3024 2300 0.5311 0.4011
0.3366 1.3590 2400 0.5186 0.3864
0.2939 1.4156 2500 0.5234 0.3934
0.2939 1.4723 2600 0.5213 0.3973
0.2939 1.5289 2700 0.5156 0.3877
0.2939 1.5855 2800 0.5052 0.3898
0.2939 1.6421 2900 0.4981 0.3833
0.2838 1.6988 3000 0.4990 0.3804
0.2838 1.7554 3100 0.5000 0.3807
0.2838 1.8120 3200 0.4961 0.3751
0.2838 1.8686 3300 0.4859 0.3731
0.2838 1.9253 3400 0.4812 0.3657
0.2694 1.9819 3500 0.4779 0.3620
0.2694 2.0385 3600 0.4943 0.3633
0.2694 2.0951 3700 0.4880 0.3677
0.2694 2.1518 3800 0.4990 0.3662
0.2694 2.2084 3900 0.5101 0.3699
0.2419 2.2650 4000 0.5393 0.3902
0.2419 2.3216 4100 0.6454 0.4513
0.2419 2.3783 4200 0.9892 0.5937
0.2419 2.4349 4300 0.7712 0.5167
0.2419 2.4915 4400 0.6338 0.4788
0.46 2.5481 4500 0.5562 0.4156
0.46 2.6048 4600 0.5377 0.3906
0.46 2.6614 4700 0.5687 0.4008
0.46 2.7180 4800 0.6321 0.4291
0.46 2.7746 4900 0.5834 0.4203
0.299 2.8313 5000 0.5302 0.3930
0.299 2.8879 5100 0.5316 0.3860
0.299 2.9445 5200 0.5344 0.3800
0.299 3.0011 5300 0.5349 0.3842
0.299 3.0578 5400 0.5776 0.4183
0.2839 3.1144 5500 0.5883 0.4100
0.2839 3.1710 5600 0.5723 0.4044
0.2839 3.2276 5700 0.5630 0.4078
0.2839 3.2843 5800 0.5810 0.4191
0.2839 3.3409 5900 0.5996 0.4228
0.3019 3.3975 6000 0.5682 0.4016
0.3019 3.4541 6100 0.5561 0.4057
0.3019 3.5108 6200 0.5905 0.4146
0.3019 3.5674 6300 0.5875 0.4190
0.3019 3.6240 6400 0.5878 0.4446
0.2944 3.6806 6500 0.5939 0.4404
0.2944 3.7373 6600 0.5903 0.4183
0.2944 3.7939 6700 0.5808 0.4059
0.2944 3.8505 6800 0.6155 0.4101
0.2944 3.9071 6900 0.7987 0.5823
0.3918 3.9638 7000 0.9750 0.5545
0.3918 4.0204 7100 1.0540 0.5689
0.3918 4.0770 7200 0.6851 0.4396
0.3918 4.1336 7300 0.7332 0.4973
0.3918 4.1903 7400 0.9466 0.6395
0.5378 4.2469 7500 0.8257 0.4851
0.5378 4.3035 7600 0.8490 0.4867
0.5378 4.3601 7700 0.8717 0.4711
0.5378 4.4168 7800 0.8839 0.5860
0.5378 4.4734 7900 2.9113 1.0
1.3847 4.5300 8000 2.8576 1.0
1.3847 4.5866 8100 2.8391 1.0
1.3847 4.6433 8200 2.8406 1.0
1.3847 4.6999 8300 2.8566 1.0
1.3847 4.7565 8400 2.8454 0.9998
2.8136 4.8131 8500 2.8340 0.9999
2.8136 4.8698 8600 2.8367 0.9999
2.8136 4.9264 8700 2.8334 0.9999
2.8136 4.9830 8800 2.8321 0.9999
2.8136 5.0396 8900 2.8025 0.9982
2.8007 5.0963 9000 2.8024 0.9975
2.8007 5.1529 9100 2.8043 0.9981
2.8007 5.2095 9200 2.8106 0.9992
2.8007 5.2661 9300 2.8067 0.9993
2.8007 5.3228 9400 2.8053 0.9986
2.7935 5.3794 9500 2.8077 0.9978
2.7935 5.4360 9600 2.8083 0.9987
2.7935 5.4926 9700 2.8080 0.9989
2.7935 5.5493 9800 2.8086 0.9986
2.7935 5.6059 9900 2.8079 0.9982
2.7861 5.6625 10000 2.8074 0.9983

Framework versions

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