Wav2vec2 Xls R 300m Okinoerabu Lr 3e 4

--- library_name: transformers license: apache-2.0 base_model: facebook/wav2vec2-xls-r-300m tags: - generated_from_trainer metrics: - wer model-index: - name: wav2vec2-xls-r-300m-okinoerabu-lr-3e-4 results: [] --- # wav2vec2-xls-r-300m-okinoerabu-lr-3e-4 This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.2382 - Cer: 0.0746 - Wer: 0.3453 ## 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: 5e-05 - train_batch_size: 16 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 32 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - num_epochs: 100 ### Training results | Training Loss | Epoch | Step | Validation Loss | Cer | Wer | |:-------------:|:-------:|:-----:|:---------------:|:------:|:------:| | 131.5963 | 0.7407 | 100 | 46.4079 | 0.9999 | 1.0 | | 71.0036 | 1.4815 | 200 | 23.6939 | 0.9999 | 1.0 | | 41.5379 | 2.2222 | 300 | 14.3187 | 0.9999 | 1.0 | | 22.4654 | 2.9630 | 400 | 7.1178 | 0.9999 | 1.0 | | 10.9829 | 3.7037 | 500 | 4.3045 | 0.9999 | 1.0 | | 8.6748 | 4.4444 | 600 | 4.1853 | 0.9999 | 1.0 | | 8.4073 | 5.1852 | 700 | 4.1068 | 0.9999 | 1.0 | | 8.2699 | 5.9259 | 800 | 4.0733 | 0.9999 | 1.0 | | 8.1201 | 6.6667 | 900 | 4.0341 | 0.9999 | 1.0 | | 8.0608 | 7.4074 | 1000 | 4.0257 | 0.9999 | 1.0 | | 8.0607 | 8.1481 | 1100 | 4.0250 | 0.9999 | 1.0 | | 8.0683 | 8.8889 | 1200 | 4.0183 | 0.9999 | 1.0 | | 8.0276 | 9.6296 | 1300 | 4.0060 | 0.9999 | 1.0 | | 8.0674 | 10.3704 | 1400 | 4.0026 | 0.9999 | 1.0 | | 7.9944 | 11.1111 | 1500 | 3.9810 | 0.9999 | 1.0 | | 7.8422 | 11.8519 | 1600 | 3.8968 | 0.9999 | 1.0 | | 7.8075 | 12.5926 | 1700 | 4.0429 | 0.9999 | 1.0 | | 7.7723 | 13.3333 | 1800 | 3.9407 | 0.9999 | 1.0 | | 7.7423 | 14.0741 | 1900 | 3.8631 | 0.9999 | 1.0 | | 7.6246 | 14.8148 | 2000 | 3.7744 | 0.9999 | 1.0 | | 7.0852 | 15.5556 | 2100 | 3.0202 | 0.9232 | 1.0 | | 4.6926 | 16.2963 | 2200 | 1.4690 | 0.3770 | 0.9971 | | 2.7306 | 17.0370 | 2300 | 0.9529 | 0.2411 | 0.9055 | | 1.9313 | 17.7778 | 2400 | 0.6734 | 0.1514 | 0.6376 | | 1.4976 | 18.5185 | 2500 | 0.5398 | 0.1303 | 0.5314 | | 1.2640 | 19.2593 | 2600 | 0.4533 | 0.1210 | 0.5166 | | 1.0471 | 20.0 | 2700 | 0.3733 | 0.1092 | 0.4789 | | 0.8940 | 20.7407 | 2800 | 0.3431 | 0.1037 | 0.4603 | | 0.7892 | 21.4815 | 2900 | 0.3114 | 0.1018 | 0.4458 | | 0.7511 | 22.2222 | 3000 | 0.2896 | 0.0999 | 0.4518 | | 0.6978 | 22.9630 | 3100 | 0.2701 | 0.0961 | 0.4435 | | 0.6512 | 23.7037 | 3200 | 0.2518 | 0.0904 | 0.4127 | | 0.6353 | 24.4444 | 3300 | 0.2388 | 0.0900 | 0.4167 | | 0.5877 | 25.1852 | 3400 | 0.2358 | 0.0879 | 0.4081 | | 0.5581 | 25.9259 | 3500 | 0.2268 | 0.0865 | 0.4055 | | 0.5597 | 26.6667 | 3600 | 0.2315 | 0.0871 | 0.4047 | | 0.5145 | 27.4074 | 3700 | 0.2172 | 0.0843 | 0.3853 | | 0.5045 | 28.1481 | 3800 | 0.2185 | 0.0859 | 0.4030 | | 0.4756 | 28.8889 | 3900 | 0.2111 | 0.0856 | 0.3958 | | 0.4855 | 29.6296 | 4000 | 0.2029 | 0.0818 | 0.3838 | | 0.4509 | 30.3704 | 4100 | 0.2024 | 0.0805 | 0.3710 | | 0.4407 | 31.1111 | 4200 | 0.2004 | 0.0808 | 0.3736 | | 0.4217 | 31.8519 | 4300 | 0.1956 | 0.0808 | 0.3761 | | 0.4120 | 32.5926 | 4400 | 0.1914 | 0.0796 | 0.3656 | | 0.3879 | 33.3333 | 4500 | 0.1915 | 0.0790 | 0.3616 | | 0.3958 | 34.0741 | 4600 | 0.1887 | 0.0788 | 0.3630 | | 0.4007 | 34.8148 | 4700 | 0.1959 | 0.0792 | 0.3673 | | 0.3981 | 35.5556 | 4800 | 0.1900 | 0.0800 | 0.3776 | | 0.3655 | 36.2963 | 4900 | 0.1870 | 0.0791 | 0.3707 | | 0.3783 | 37.0370 | 5000 | 0.1841 | 0.0779 | 0.3576 | | 0.3484 | 37.7778 | 5100 | 0.1909 | 0.0789 | 0.3639 | | 0.3473 | 38.5185 | 5200 | 0.1902 | 0.0789 | 0.3650 | | 0.3570 | 39.2593 | 5300 | 0.2105 | 0.0850 | 0.4018 | | 0.3128 | 40.0 | 5400 | 0.1876 | 0.0799 | 0.3701 | | 0.3288 | 40.7407 | 5500 | 0.1868 | 0.0786 | 0.3587 | | 0.3266 | 41.4815 | 5600 | 0.1923 | 0.0784 | 0.3656 | | 0.3209 | 42.2222 | 5700 | 0.2073 | 0.0824 | 0.3827 | | 0.3029 | 42.9630 | 5800 | 0.2026 | 0.0800 | 0.3704 | | 0.2941 | 43.7037 | 5900 | 0.2073 | 0.0812 | 0.3759 | | 0.2999 | 44.4444 | 6000 | 0.1927 | 0.0787 | 0.3679 | | 0.2910 | 45.1852 | 6100 | 0.2042 | 0.0813 | 0.3659 | | 0.2986 | 45.9259 | 6200 | 0.1964 | 0.0772 | 0.3610 | | 0.2894 | 46.6667 | 6300 | 0.2038 | 0.0799 | 0.3679 | | 0.2714 | 47.4074 | 6400 | 0.1990 | 0.0774 | 0.3607 | | 0.2871 | 48.1481 | 6500 | 0.2023 | 0.0777 | 0.3636 | | 0.2673 | 48.8889 | 6600 | 0.1973 | 0.0763 | 0.3599 | | 0.2688 | 49.6296 | 6700 | 0.1944 | 0.0774 | 0.3624 | | 0.2561 | 50.3704 | 6800 | 0.2042 | 0.0772 | 0.3593 | | 0.2455 | 51.1111 | 6900 | 0.1952 | 0.0775 | 0.3647 | | 0.2403 | 51.8519 | 7000 | 0.1945 | 0.0767 | 0.3604 | | 0.2440 | 52.5926 | 7100 | 0.1937 | 0.0764 | 0.3567 | | 0.2321 | 53.3333 | 7200 | 0.2021 | 0.0793 | 0.3647 | | 0.2126 | 54.0741 | 7300 | 0.2022 | 0.0765 | 0.3590 | | 0.2194 | 54.8148 | 7400 | 0.1993 | 0.0777 | 0.3604 | | 0.2286 | 55.5556 | 7500 | 0.1952 | 0.0762 | 0.3556 | | 0.2192 | 56.2963 | 7600 | 0.2141 | 0.0784 | 0.3690 | | 0.2153 | 57.0370 | 7700 | 0.2049 | 0.0759 | 0.3527 | | 0.2148 | 57.7778 | 7800 | 0.2082 | 0.0768 | 0.3582 | | 0.2187 | 58.5185 | 7900 | 0.2012 | 0.0777 | 0.3610 | | 0.2042 | 59.2593 | 8000 | 0.2080 | 0.0757 | 0.3527 | | 0.1981 | 60.0 | 8100 | 0.2131 | 0.0790 | 0.3673 | | 0.2118 | 60.7407 | 8200 | 0.2144 | 0.0780 | 0.3604 | | 0.2011 | 61.4815 | 8300 | 0.2156 | 0.0773 | 0.3564 | | 0.1978 | 62.2222 | 8400 | 0.2095 | 0.0759 | 0.3545 | | 0.1859 | 62.9630 | 8500 | 0.2294 | 0.0788 | 0.3604 | | 0.1960 | 63.7037 | 8600 | 0.2088 | 0.0762 | 0.3533 | | 0.1895 | 64.4444 | 8700 | 0.2243 | 0.0795 | 0.3650 | | 0.1895 | 65.1852 | 8800 | 0.2174 | 0.0750 | 0.3527 | | 0.1859 | 65.9259 | 8900 | 0.2250 | 0.0792 | 0.3619 | | 0.1800 | 66.6667 | 9000 | 0.2129 | 0.0767 | 0.3522 | | 0.1851 | 67.4074 | 9100 | 0.2139 | 0.0768 | 0.3542 | | 0.1767 | 68.1481 | 9200 | 0.2121 | 0.0746 | 0.3479 | | 0.1806 | 68.8889 | 9300 | 0.2152 | 0.0754 | 0.3510 | | 0.1861 | 69.6296 | 9400 | 0.2201 | 0.0751 | 0.3522 | | 0.1805 | 70.3704 | 9500 | 0.2134 | 0.0760 | 0.3513 | | 0.1842 | 71.1111 | 9600 | 0.2196 | 0.0765 | 0.3539 | | 0.1688 | 71.8519 | 9700 | 0.2192 | 0.0763 | 0.3547 | | 0.1647 | 72.5926 | 9800 | 0.2215 | 0.0746 | 0.3467 | | 0.1804 | 73.3333 | 9900 | 0.2216 | 0.0743 | 0.3482 | | 0.1554 | 74.0741 | 10000 | 0.2284 | 0.0759 | 0.3536 | | 0.1647 | 74.8148 | 10100 | 0.2185 | 0.0758 | 0.3485 | | 0.1655 | 75.5556 | 10200 | 0.2168 | 0.0757 | 0.3545 | | 0.1522 | 76.2963 | 10300 | 0.2223 | 0.0755 | 0.3505 | | 0.1566 | 77.0370 | 10400 | 0.2200 | 0.0746 | 0.3459 | | 0.1544 | 77.7778 | 10500 | 0.2279 | 0.0755 | 0.3493 | | 0.1586 | 78.5185 | 10600 | 0.2254 | 0.0754 | 0.3513 | | 0.1471 | 79.2593 | 10700 | 0.2229 | 0.0754 | 0.3536 | | 0.1531 | 80.0 | 10800 | 0.2248 | 0.0760 | 0.3516 | | 0.1539 | 80.7407 | 10900 | 0.2330 | 0.0760 | 0.3487 | | 0.1543 | 81.4815 | 11000 | 0.2251 | 0.0755 | 0.3533 | | 0.1546 | 82.2222 | 11100 | 0.2318 | 0.0757 | 0.3490 | | 0.1453 | 82.9630 | 11200 | 0.2294 | 0.0758 | 0.3539 | | 0.1492 | 83.7037 | 11300 | 0.2301 | 0.0759 | 0.3513 | | 0.1569 | 84.4444 | 11400 | 0.2324 | 0.0741 | 0.3462 | | 0.1474 | 85.1852 | 11500 | 0.2335 | 0.0751 | 0.3482 | | 0.1389 | 85.9259 | 11600 | 0.2322 | 0.0750 | 0.3507 | | 0.1450 | 86.6667 | 11700 | 0.2376 | 0.0744 | 0.3462 | | 0.1448 | 87.4074 | 11800 | 0.2413 | 0.0753 | 0.3490 | | 0.1440 | 88.1481 | 11900 | 0.2378 | 0.0749 | 0.3465 | | 0.1384 | 88.8889 | 12000 | 0.2396 | 0.0741 | 0.3465 | | 0.1486 | 89.6296 | 12100 | 0.2375 | 0.0749 | 0.3473 | | 0.1404 | 90.3704 | 12200 | 0.2349 | 0.0747 | 0.3487 | | 0.1377 | 91.1111 | 12300 | 0.2362 | 0.0747 | 0.3479 | | 0.1428 | 91.8519 | 12400 | 0.2344 | 0.0749 | 0.3476 | | 0.1446 | 92.5926 | 12500 | 0.2327 | 0.0746 | 0.3465 | | 0.1378 | 93.3333 | 12600 | 0.2337 | 0.0748 | 0.3467 | | 0.1337 | 94.0741 | 12700 | 0.2357 | 0.0744 | 0.3447 | | 0.1376 | 94.8148 | 12800 | 0.2346 | 0.0746 | 0.3470 | | 0.1311 | 95.5556 | 12900 | 0.2377 | 0.0749 | 0.3485 | | 0.1318 | 96.2963 | 13000 | 0.2370 | 0.0750 | 0.3465 | | 0.1359 | 97.0370 | 13100 | 0.2385 | 0.0747 | 0.3473 | | 0.1418 | 97.7778 | 13200 | 0.2383 | 0.0743 | 0.3445 | | 0.1364 | 98.5185 | 13300 | 0.2383 | 0.0747 | 0.3450 | | 0.1196 | 99.2593 | 13400 | 0.2380 | 0.0742 | 0.3436 | | 0.1342 | 100.0 | 13500 | 0.2382 | 0.0746 | 0.3453 | ### Framework versions - Transformers 5.8.1 - Pytorch 2.11.0+cu128 - Datasets 3.6.0 - Tokenizers 0.22.2