--- license: cc-by-nc-4.0 base_model: facebook/mms-1b-all tags: - generated_from_trainer metrics: - wer model-index: - name: mms-lug results: [] --- # mms-lug This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the None dataset. It achieves the following results on the evaluation set: - Loss: inf - Wer: 0.1745 ## 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: 0.001 - 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: 100 - num_epochs: 5 ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | |:-------------:|:-----:|:----:|:---------------:|:------:| | No log | 0.02 | 20 | inf | 1.0049 | | No log | 0.04 | 40 | inf | 1.0 | | No log | 0.07 | 60 | inf | 0.3009 | | No log | 0.09 | 80 | inf | 0.1998 | | 4.042 | 0.11 | 100 | inf | 0.2110 | | 4.042 | 0.13 | 120 | inf | 0.2047 | | 4.042 | 0.15 | 140 | inf | 0.2040 | | 4.042 | 0.17 | 160 | inf | 0.1949 | | 4.042 | 0.2 | 180 | inf | 0.2026 | | 0.3406 | 0.22 | 200 | inf | 0.1833 | | 0.3406 | 0.24 | 220 | inf | 0.1875 | | 0.3406 | 0.26 | 240 | inf | 0.2128 | | 0.3406 | 0.28 | 260 | inf | 0.1910 | | 0.3406 | 0.3 | 280 | inf | 0.1798 | | 0.2831 | 0.33 | 300 | inf | 0.1749 | | 0.2831 | 0.35 | 320 | inf | 0.1875 | | 0.2831 | 0.37 | 340 | inf | 0.1780 | | 0.2831 | 0.39 | 360 | inf | 0.1907 | | 0.2831 | 0.41 | 380 | inf | 0.2005 | | 0.2796 | 0.43 | 400 | inf | 0.2037 | | 0.2796 | 0.46 | 420 | inf | 0.1973 | | 0.2796 | 0.48 | 440 | inf | 0.1917 | | 0.2796 | 0.5 | 460 | inf | 0.2015 | | 0.2796 | 0.52 | 480 | inf | 0.1784 | | 0.3198 | 0.54 | 500 | inf | 0.1812 | | 0.3198 | 0.56 | 520 | inf | 0.1808 | | 0.3198 | 0.59 | 540 | inf | 0.1987 | | 0.3198 | 0.61 | 560 | inf | 0.1696 | | 0.3198 | 0.63 | 580 | inf | 0.1710 | | 0.3131 | 0.65 | 600 | inf | 0.1794 | | 0.3131 | 0.67 | 620 | inf | 0.1773 | | 0.3131 | 0.69 | 640 | inf | 0.1777 | | 0.3131 | 0.72 | 660 | inf | 0.2005 | | 0.3131 | 0.74 | 680 | inf | 0.1886 | | 0.2777 | 0.76 | 700 | inf | 0.2058 | | 0.2777 | 0.78 | 720 | inf | 0.1770 | | 0.2777 | 0.8 | 740 | inf | 0.1801 | | 0.2777 | 0.83 | 760 | inf | 0.1914 | | 0.2777 | 0.85 | 780 | inf | 0.1770 | | 0.2694 | 0.87 | 800 | inf | 0.1815 | | 0.2694 | 0.89 | 820 | inf | 0.1717 | | 0.2694 | 0.91 | 840 | inf | 0.1777 | | 0.2694 | 0.93 | 860 | inf | 0.1671 | | 0.2694 | 0.96 | 880 | inf | 0.1706 | | 0.3216 | 0.98 | 900 | inf | 0.2381 | | 0.3216 | 1.0 | 920 | inf | 0.1766 | | 0.3216 | 1.02 | 940 | inf | 0.1826 | | 0.3216 | 1.04 | 960 | inf | 0.1749 | | 0.3216 | 1.06 | 980 | inf | 0.1836 | | 0.3008 | 1.09 | 1000 | inf | 0.1696 | | 0.3008 | 1.11 | 1020 | inf | 0.1703 | | 0.3008 | 1.13 | 1040 | inf | 0.1703 | | 0.3008 | 1.15 | 1060 | inf | 0.1942 | | 0.3008 | 1.17 | 1080 | inf | 0.1780 | | 0.2621 | 1.19 | 1100 | inf | 0.1626 | | 0.2621 | 1.22 | 1120 | inf | 0.1728 | | 0.2621 | 1.24 | 1140 | inf | 0.1738 | | 0.2621 | 1.26 | 1160 | inf | 0.1745 | | 0.2621 | 1.28 | 1180 | inf | 0.1766 | | 0.2837 | 1.3 | 1200 | inf | 0.1685 | | 0.2837 | 1.32 | 1220 | inf | 0.1647 | | 0.2837 | 1.35 | 1240 | inf | 0.1664 | | 0.2837 | 1.37 | 1260 | inf | 0.1784 | | 0.2837 | 1.39 | 1280 | inf | 0.1699 | | 0.2648 | 1.41 | 1300 | inf | 0.1713 | | 0.2648 | 1.43 | 1320 | inf | 0.1749 | | 0.2648 | 1.45 | 1340 | inf | 0.1692 | | 0.2648 | 1.48 | 1360 | inf | 0.1808 | | 0.2648 | 1.5 | 1380 | inf | 0.1724 | | 0.3012 | 1.52 | 1400 | inf | 0.1710 | | 0.3012 | 1.54 | 1420 | inf | 0.1668 | | 0.3012 | 1.56 | 1440 | inf | 0.1724 | | 0.3012 | 1.59 | 1460 | inf | 0.1763 | | 0.3012 | 1.61 | 1480 | inf | 0.1868 | | 0.287 | 1.63 | 1500 | inf | 0.1675 | | 0.287 | 1.65 | 1520 | inf | 0.1728 | | 0.287 | 1.67 | 1540 | inf | 0.1661 | | 0.287 | 1.69 | 1560 | inf | 0.1657 | | 0.287 | 1.72 | 1580 | inf | 0.1794 | | 0.2042 | 1.74 | 1600 | inf | 0.1685 | | 0.2042 | 1.76 | 1620 | inf | 0.1956 | | 0.2042 | 1.78 | 1640 | inf | 0.1594 | | 0.2042 | 1.8 | 1660 | inf | 0.1626 | | 0.2042 | 1.82 | 1680 | inf | 0.1559 | | 0.3219 | 1.85 | 1700 | inf | 0.1612 | | 0.3219 | 1.87 | 1720 | inf | 0.1759 | | 0.3219 | 1.89 | 1740 | inf | 0.1742 | | 0.3219 | 1.91 | 1760 | inf | 0.1738 | | 0.3219 | 1.93 | 1780 | inf | 0.1640 | | 0.2695 | 1.95 | 1800 | inf | 0.1678 | | 0.2695 | 1.98 | 1820 | inf | 0.1615 | | 0.2695 | 2.0 | 1840 | inf | 0.1685 | | 0.2695 | 2.02 | 1860 | inf | 0.1650 | | 0.2695 | 2.04 | 1880 | inf | 0.1682 | | 0.2759 | 2.06 | 1900 | inf | 0.1938 | | 0.2759 | 2.08 | 1920 | inf | 0.1629 | | 0.2759 | 2.11 | 1940 | inf | 0.1587 | | 0.2759 | 2.13 | 1960 | inf | 0.1566 | | 0.2759 | 2.15 | 1980 | inf | 0.1605 | | 0.2584 | 2.17 | 2000 | inf | 0.1699 | | 0.2584 | 2.19 | 2020 | inf | 0.1780 | | 0.2584 | 2.21 | 2040 | inf | 0.1664 | | 0.2584 | 2.24 | 2060 | inf | 0.1629 | | 0.2584 | 2.26 | 2080 | inf | 0.1699 | | 0.2618 | 2.28 | 2100 | inf | 0.1629 | | 0.2618 | 2.3 | 2120 | inf | 0.1692 | | 0.2618 | 2.32 | 2140 | inf | 0.1706 | | 0.2618 | 2.35 | 2160 | inf | 0.1675 | | 0.2618 | 2.37 | 2180 | inf | 0.1696 | | 0.278 | 2.39 | 2200 | inf | 0.1626 | | 0.278 | 2.41 | 2220 | inf | 0.1612 | | 0.278 | 2.43 | 2240 | inf | 0.1696 | | 0.278 | 2.45 | 2260 | inf | 0.1654 | | 0.278 | 2.48 | 2280 | inf | 0.1668 | | 0.2213 | 2.5 | 2300 | inf | 0.1678 | | 0.2213 | 2.52 | 2320 | inf | 0.1745 | | 0.2213 | 2.54 | 2340 | inf | 0.1640 | | 0.2213 | 2.56 | 2360 | inf | 0.1608 | | 0.2213 | 2.58 | 2380 | inf | 0.1573 | | 0.2187 | 2.61 | 2400 | inf | 0.1657 | | 0.2187 | 2.63 | 2420 | inf | 0.1587 | | 0.2187 | 2.65 | 2440 | inf | 0.1622 | | 0.2187 | 2.67 | 2460 | inf | 0.1717 | | 0.2187 | 2.69 | 2480 | inf | 0.1562 | | 0.2585 | 2.71 | 2500 | inf | 0.1573 | | 0.2585 | 2.74 | 2520 | inf | 0.1566 | | 0.2585 | 2.76 | 2540 | inf | 0.1742 | | 0.2585 | 2.78 | 2560 | inf | 0.1605 | | 0.2585 | 2.8 | 2580 | inf | 0.1605 | | 0.2913 | 2.82 | 2600 | inf | 0.1745 | | 0.2913 | 2.84 | 2620 | inf | 0.1608 | | 0.2913 | 2.87 | 2640 | inf | 0.1615 | | 0.2913 | 2.89 | 2660 | inf | 0.1675 | | 0.2913 | 2.91 | 2680 | inf | 0.1612 | | 0.2743 | 2.93 | 2700 | inf | 0.1577 | | 0.2743 | 2.95 | 2720 | inf | 0.1598 | | 0.2743 | 2.98 | 2740 | inf | 0.1566 | | 0.2743 | 3.0 | 2760 | inf | 0.1573 | | 0.2743 | 3.02 | 2780 | inf | 0.1594 | | 0.2854 | 3.04 | 2800 | inf | 0.1608 | | 0.2854 | 3.06 | 2820 | inf | 0.1650 | | 0.2854 | 3.08 | 2840 | inf | 0.1580 | | 0.2854 | 3.11 | 2860 | inf | 0.1640 | | 0.2854 | 3.13 | 2880 | inf | 0.1594 | | 0.243 | 3.15 | 2900 | inf | 0.1601 | | 0.243 | 3.17 | 2920 | inf | 0.1703 | | 0.243 | 3.19 | 2940 | inf | 0.1573 | | 0.243 | 3.21 | 2960 | inf | 0.1587 | | 0.243 | 3.24 | 2980 | inf | 0.1668 | | 0.2563 | 3.26 | 3000 | inf | 0.1713 | | 0.2563 | 3.28 | 3020 | inf | 0.1570 | | 0.2563 | 3.3 | 3040 | inf | 0.1601 | | 0.2563 | 3.32 | 3060 | inf | 0.1619 | | 0.2563 | 3.34 | 3080 | inf | 0.1541 | | 0.228 | 3.37 | 3100 | inf | 0.1552 | | 0.228 | 3.39 | 3120 | inf | 0.1566 | | 0.228 | 3.41 | 3140 | inf | 0.1552 | | 0.228 | 3.43 | 3160 | inf | 0.1619 | | 0.228 | 3.45 | 3180 | inf | 0.1657 | | 0.2684 | 3.47 | 3200 | inf | 0.1622 | | 0.2684 | 3.5 | 3220 | inf | 0.1548 | | 0.2684 | 3.52 | 3240 | inf | 0.1608 | | 0.2684 | 3.54 | 3260 | inf | 0.1664 | | 0.2684 | 3.56 | 3280 | inf | 0.1594 | | 0.2623 | 3.58 | 3300 | inf | 0.1650 | | 0.2623 | 3.6 | 3320 | inf | 0.1541 | | 0.2623 | 3.63 | 3340 | inf | 0.1555 | | 0.2623 | 3.65 | 3360 | inf | 0.1598 | | 0.2623 | 3.67 | 3380 | inf | 0.1629 | | 0.2573 | 3.69 | 3400 | inf | 0.1584 | | 0.2573 | 3.71 | 3420 | inf | 0.1650 | | 0.2573 | 3.74 | 3440 | inf | 0.1612 | | 0.2573 | 3.76 | 3460 | inf | 0.1615 | | 0.2573 | 3.78 | 3480 | inf | 0.1584 | | 0.2698 | 3.8 | 3500 | inf | 0.1591 | | 0.2698 | 3.82 | 3520 | inf | 0.1601 | | 0.2698 | 3.84 | 3540 | inf | 0.1626 | | 0.2698 | 3.87 | 3560 | inf | 0.1566 | | 0.2698 | 3.89 | 3580 | inf | 0.1699 | | 0.2178 | 3.91 | 3600 | inf | 0.1647 | | 0.2178 | 3.93 | 3620 | inf | 0.1608 | | 0.2178 | 3.95 | 3640 | inf | 0.1703 | | 0.2178 | 3.97 | 3660 | inf | 0.1717 | | 0.2178 | 4.0 | 3680 | inf | 0.1626 | | 0.2964 | 4.02 | 3700 | inf | 0.1612 | | 0.2964 | 4.04 | 3720 | inf | 0.1671 | | 0.2964 | 4.06 | 3740 | inf | 0.1682 | | 0.2964 | 4.08 | 3760 | inf | 0.1738 | | 0.2964 | 4.1 | 3780 | inf | 0.1728 | | 0.2778 | 4.13 | 3800 | inf | 0.1879 | | 0.2778 | 4.15 | 3820 | inf | 0.1633 | | 0.2778 | 4.17 | 3840 | inf | 0.1675 | | 0.2778 | 4.19 | 3860 | inf | 0.1657 | | 0.2778 | 4.21 | 3880 | inf | 0.1879 | | 0.292 | 4.23 | 3900 | inf | 0.1664 | | 0.292 | 4.26 | 3920 | inf | 0.1699 | | 0.292 | 4.28 | 3940 | inf | 0.1822 | | 0.292 | 4.3 | 3960 | inf | 0.1678 | | 0.292 | 4.32 | 3980 | inf | 0.1682 | | 0.2267 | 4.34 | 4000 | inf | 0.1654 | | 0.2267 | 4.36 | 4020 | inf | 0.1724 | | 0.2267 | 4.39 | 4040 | inf | 0.1777 | | 0.2267 | 4.41 | 4060 | inf | 0.1721 | | 0.2267 | 4.43 | 4080 | inf | 0.1770 | | 0.2807 | 4.45 | 4100 | inf | 0.1717 | | 0.2807 | 4.47 | 4120 | inf | 0.1773 | | 0.2807 | 4.5 | 4140 | inf | 0.1777 | | 0.2807 | 4.52 | 4160 | inf | 0.1657 | | 0.2807 | 4.54 | 4180 | inf | 0.1692 | | 0.2953 | 4.56 | 4200 | inf | 0.1699 | | 0.2953 | 4.58 | 4220 | inf | 0.1650 | | 0.2953 | 4.6 | 4240 | inf | 0.1731 | | 0.2953 | 4.63 | 4260 | inf | 0.1685 | | 0.2953 | 4.65 | 4280 | inf | 0.1721 | | 0.2463 | 4.67 | 4300 | inf | 0.1643 | | 0.2463 | 4.69 | 4320 | inf | 0.1636 | | 0.2463 | 4.71 | 4340 | inf | 0.1657 | | 0.2463 | 4.73 | 4360 | inf | 0.1678 | | 0.2463 | 4.76 | 4380 | inf | 0.1759 | | 0.313 | 4.78 | 4400 | inf | 0.1682 | | 0.313 | 4.8 | 4420 | inf | 0.1671 | | 0.313 | 4.82 | 4440 | inf | 0.1713 | | 0.313 | 4.84 | 4460 | inf | 0.1675 | | 0.313 | 4.86 | 4480 | inf | 0.1808 | | 0.2748 | 4.89 | 4500 | inf | 0.1713 | | 0.2748 | 4.91 | 4520 | inf | 0.1812 | | 0.2748 | 4.93 | 4540 | inf | 0.1731 | | 0.2748 | 4.95 | 4560 | inf | 0.1738 | | 0.2748 | 4.97 | 4580 | inf | 0.1728 | | 0.279 | 4.99 | 4600 | inf | 0.1745 | ### Framework versions - Transformers 4.32.0.dev0 - Pytorch 2.0.1+cu117 - Datasets 2.13.0 - Tokenizers 0.13.3