--- 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](https://huggingface.co/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: 0.4061 - Wer: 0.3191 ## 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: 10000 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | |:-------------:|:------:|:-----:|:---------------:|:------:| | No log | 0.0194 | 100 | 3.5565 | 1.0 | | No log | 0.0387 | 200 | 3.0302 | 1.0 | | No log | 0.0581 | 300 | 2.9461 | 1.0 | | No log | 0.0774 | 400 | 1.8143 | 0.9407 | | 3.9521 | 0.0968 | 500 | 1.4196 | 0.8693 | | 3.9521 | 0.1161 | 600 | 1.1669 | 0.8055 | | 3.9521 | 0.1355 | 700 | 1.0757 | 0.7596 | | 3.9521 | 0.1549 | 800 | 0.9945 | 0.7224 | | 3.9521 | 0.1742 | 900 | 0.9381 | 0.6871 | | 1.0266 | 0.1936 | 1000 | 0.8978 | 0.6615 | | 1.0266 | 0.2129 | 1100 | 0.8771 | 0.6450 | | 1.0266 | 0.2323 | 1200 | 0.8516 | 0.6404 | | 1.0266 | 0.2516 | 1300 | 0.8274 | 0.6138 | | 1.0266 | 0.2710 | 1400 | 0.7993 | 0.5970 | | 0.8454 | 0.2904 | 1500 | 0.7769 | 0.5888 | | 0.8454 | 0.3097 | 1600 | 0.7664 | 0.5998 | | 0.8454 | 0.3291 | 1700 | 0.7401 | 0.5592 | | 0.8454 | 0.3484 | 1800 | 0.7465 | 0.5650 | | 0.8454 | 0.3678 | 1900 | 0.7253 | 0.5791 | | 0.7537 | 0.3871 | 2000 | 0.7039 | 0.5344 | | 0.7537 | 0.4065 | 2100 | 0.6932 | 0.5168 | | 0.7537 | 0.4259 | 2200 | 0.6969 | 0.5364 | | 0.7537 | 0.4452 | 2300 | 0.6781 | 0.5174 | | 0.7537 | 0.4646 | 2400 | 0.6761 | 0.5050 | | 0.681 | 0.4839 | 2500 | 0.6721 | 0.5287 | | 0.681 | 0.5033 | 2600 | 0.6598 | 0.5195 | | 0.681 | 0.5226 | 2700 | 0.6555 | 0.4976 | | 0.681 | 0.5420 | 2800 | 0.6535 | 0.4994 | | 0.681 | 0.5614 | 2900 | 0.6259 | 0.4819 | | 0.6737 | 0.5807 | 3000 | 0.6299 | 0.4802 | | 0.6737 | 0.6001 | 3100 | 0.6379 | 0.4893 | | 0.6737 | 0.6194 | 3200 | 0.6226 | 0.4806 | | 0.6737 | 0.6388 | 3300 | 0.6089 | 0.4627 | | 0.6737 | 0.6581 | 3400 | 0.6029 | 0.4735 | | 0.6419 | 0.6775 | 3500 | 0.5871 | 0.4592 | | 0.6419 | 0.6969 | 3600 | 0.6001 | 0.4611 | | 0.6419 | 0.7162 | 3700 | 0.5849 | 0.4473 | | 0.6419 | 0.7356 | 3800 | 0.5924 | 0.4638 | | 0.6419 | 0.7549 | 3900 | 0.5768 | 0.4585 | | 0.6183 | 0.7743 | 4000 | 0.5673 | 0.4453 | | 0.6183 | 0.7937 | 4100 | 0.5575 | 0.4452 | | 0.6183 | 0.8130 | 4200 | 0.5632 | 0.4475 | | 0.6183 | 0.8324 | 4300 | 0.5499 | 0.4401 | | 0.6183 | 0.8517 | 4400 | 0.5663 | 0.4310 | | 0.5877 | 0.8711 | 4500 | 0.5585 | 0.4317 | | 0.5877 | 0.8904 | 4600 | 0.5464 | 0.4200 | | 0.5877 | 0.9098 | 4700 | 0.5381 | 0.4192 | | 0.5877 | 0.9292 | 4800 | 0.5454 | 0.4202 | | 0.5877 | 0.9485 | 4900 | 0.5238 | 0.4124 | | 0.5621 | 0.9679 | 5000 | 0.5304 | 0.4135 | | 0.5621 | 0.9872 | 5100 | 0.5163 | 0.4061 | | 0.5621 | 1.0066 | 5200 | 0.5160 | 0.3993 | | 0.5621 | 1.0259 | 5300 | 0.5089 | 0.3899 | | 0.5621 | 1.0453 | 5400 | 0.5111 | 0.3986 | | 0.4882 | 1.0647 | 5500 | 0.5010 | 0.3857 | | 0.4882 | 1.0840 | 5600 | 0.4941 | 0.3859 | | 0.4882 | 1.1034 | 5700 | 0.4940 | 0.3813 | | 0.4882 | 1.1227 | 5800 | 0.4914 | 0.3782 | | 0.4882 | 1.1421 | 5900 | 0.4875 | 0.3745 | | 0.4569 | 1.1614 | 6000 | 0.4842 | 0.3807 | | 0.4569 | 1.1808 | 6100 | 0.4861 | 0.3737 | | 0.4569 | 1.2002 | 6200 | 0.4814 | 0.3761 | | 0.4569 | 1.2195 | 6300 | 0.4781 | 0.3741 | | 0.4569 | 1.2389 | 6400 | 0.4771 | 0.3682 | | 0.4416 | 1.2582 | 6500 | 0.4710 | 0.3734 | | 0.4416 | 1.2776 | 6600 | 0.4721 | 0.3660 | | 0.4416 | 1.2969 | 6700 | 0.4679 | 0.3639 | | 0.4416 | 1.3163 | 6800 | 0.4623 | 0.3665 | | 0.4416 | 1.3357 | 6900 | 0.4611 | 0.3602 | | 0.4324 | 1.3550 | 7000 | 0.4689 | 0.3609 | | 0.4324 | 1.3744 | 7100 | 0.4573 | 0.3603 | | 0.4324 | 1.3937 | 7200 | 0.4575 | 0.3546 | | 0.4324 | 1.4131 | 7300 | 0.4556 | 0.3584 | | 0.4324 | 1.4324 | 7400 | 0.4496 | 0.3507 | | 0.4255 | 1.4518 | 7500 | 0.4461 | 0.3467 | | 0.4255 | 1.4712 | 7600 | 0.4434 | 0.3462 | | 0.4255 | 1.4905 | 7700 | 0.4436 | 0.3516 | | 0.4255 | 1.5099 | 7800 | 0.4406 | 0.3458 | | 0.4255 | 1.5292 | 7900 | 0.4387 | 0.3439 | | 0.4094 | 1.5486 | 8000 | 0.4325 | 0.3410 | | 0.4094 | 1.5679 | 8100 | 0.4360 | 0.3419 | | 0.4094 | 1.5873 | 8200 | 0.4286 | 0.3377 | | 0.4094 | 1.6067 | 8300 | 0.4301 | 0.3336 | | 0.4094 | 1.6260 | 8400 | 0.4297 | 0.3323 | | 0.4018 | 1.6454 | 8500 | 0.4270 | 0.3339 | | 0.4018 | 1.6647 | 8600 | 0.4267 | 0.3320 | | 0.4018 | 1.6841 | 8700 | 0.4224 | 0.3328 | | 0.4018 | 1.7034 | 8800 | 0.4207 | 0.3298 | | 0.4018 | 1.7228 | 8900 | 0.4197 | 0.3298 | | 0.3899 | 1.7422 | 9000 | 0.4184 | 0.3258 | | 0.3899 | 1.7615 | 9100 | 0.4165 | 0.3262 | | 0.3899 | 1.7809 | 9200 | 0.4118 | 0.3229 | | 0.3899 | 1.8002 | 9300 | 0.4134 | 0.3232 | | 0.3899 | 1.8196 | 9400 | 0.4127 | 0.3209 | | 0.3665 | 1.8389 | 9500 | 0.4108 | 0.3211 | | 0.3665 | 1.8583 | 9600 | 0.4090 | 0.3199 | | 0.3665 | 1.8777 | 9700 | 0.4076 | 0.3209 | | 0.3665 | 1.8970 | 9800 | 0.4065 | 0.3198 | | 0.3665 | 1.9164 | 9900 | 0.4062 | 0.3192 | | 0.3698 | 1.9357 | 10000 | 0.4061 | 0.3193 | ### Framework versions - Transformers 4.40.2 - Pytorch 2.3.0+cu121 - Datasets 2.19.1 - Tokenizers 0.19.1