--- license: apache-2.0 tags: - automatic-speech-recognition - /workspace/data/hy/noizy_student_2/ - generated_from_trainer model-index: - name: '' results: [] --- # This model is a fine-tuned version of [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on the /WORKSPACE/DATA/HY/NOIZY_STUDENT_2/ - NA dataset. It achieves the following results on the evaluation set: - Loss: 0.2249 - Wer: 0.2783 - Cer: 0.0508 ## 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: 8e-05 - train_batch_size: 16 - eval_batch_size: 64 - seed: 842 - gradient_accumulation_steps: 8 - total_train_batch_size: 128 - optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - training_steps: 1600 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | Cer | |:-------------:|:-----:|:----:|:---------------:|:------:|:------:| | 4.9923 | 3.84 | 100 | 3.1562 | 1.0 | 1.0 | | 2.1775 | 7.69 | 200 | 0.4334 | 0.5804 | 0.1122 | | 1.3708 | 11.53 | 300 | 0.3106 | 0.4336 | 0.0797 | | 1.2266 | 15.38 | 400 | 0.2675 | 0.3673 | 0.0673 | | 1.093 | 19.23 | 500 | 0.2416 | 0.3501 | 0.0633 | | 0.989 | 23.08 | 600 | 0.2320 | 0.3251 | 0.0611 | | 0.9518 | 26.91 | 700 | 0.2413 | 0.3193 | 0.0584 | | 0.9075 | 30.76 | 800 | 0.2354 | 0.3201 | 0.0593 | | 0.878 | 34.61 | 900 | 0.2278 | 0.3126 | 0.0579 | | 0.8563 | 38.46 | 1000 | 0.2327 | 0.2963 | 0.0548 | | 0.8084 | 42.3 | 1100 | 0.2271 | 0.2923 | 0.0541 | | 0.7845 | 46.15 | 1200 | 0.2333 | 0.2951 | 0.0537 | | 0.7487 | 49.99 | 1300 | 0.2290 | 0.2888 | 0.0525 | | 0.7182 | 53.84 | 1400 | 0.2341 | 0.2877 | 0.0535 | | 0.7095 | 57.69 | 1500 | 0.2291 | 0.2818 | 0.0515 | | 0.6953 | 61.53 | 1600 | 0.2249 | 0.2783 | 0.0508 | ### Framework versions - Transformers 4.17.0.dev0 - Pytorch 1.10.2+cu102 - Datasets 1.18.2.dev0 - Tokenizers 0.11.0