Downloads · 30 days
2
8% of all-time downloads
tuanio/w2v2_ablation_with_3-layer-ling_head-best_on_tp0.025_tl10_fp0.001_fl16
w2v2_ablation_with_3-layer-ling_head-best_on_tp0.025_tl10_fp0.001_fl16 is a machine learning model from tuanio. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as cc-by-nc-4.0.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
2
8% of all-time downloads
All-time downloads
24
Public
Parameters
112M
23.8 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors225 MB · 100%
From the Hugging Face model README
This model is a fine-tuned version of nguyenvulebinh/wav2vec2-base-vietnamese-250h on an unknown dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 117.6275 | 0.94 | 100 | 86.7993 | 18.6401 |
| 80.7347 | 1.89 | 200 | 60.6786 | 18.6868 |
| 15.5452 | 2.83 | 300 | 5.4455 | 1.0 |
| 4.8823 | 3.77 | 400 | 4.8966 | 1.0 |
| 4.5817 | 4.72 | 500 | 4.7119 | 1.0 |
| 4.4462 | 5.66 | 600 | 4.6786 | 1.0 |
| 4.3818 | 6.6 | 700 | 4.6009 | 1.0 |
| 4.3461 | 7.55 | 800 | 4.5843 | 1.0 |
| 4.1749 | 8.49 | 900 | 4.2669 | 0.9994 |
| 3.9328 | 9.43 | 1000 | 3.4648 | 0.9101 |
| 2.8664 | 10.38 | 1100 | 1.6405 | 0.3230 |
| 1.4814 | 11.32 | 1200 | 1.0288 | 0.2184 |
| 1.0621 | 12.26 | 1300 | 0.8278 | 0.1763 |
| 0.8355 | 13.21 | 1400 | 0.7197 | 0.1614 |
| 0.7442 | 14.15 | 1500 | 0.6630 | 0.1746 |
| 0.6224 | 15.09 | 1600 | 0.6056 | 0.1605 |
| 0.5993 | 16.04 | 1700 | 0.5650 | 0.1572 |
| 0.5508 | 16.98 | 1800 | 0.5224 | 0.1597 |
| 0.482 | 17.92 | 1900 | 0.5072 | 0.1571 |
| 0.49 | 18.87 | 2000 | 0.5143 | 0.1610 |
| 0.4337 | 19.81 | 2100 | 0.4952 | 0.1710 |
| 0.4322 | 20.75 | 2200 | 0.4727 | 0.1554 |
| 0.4007 | 21.7 | 2300 | 0.4616 | 0.1547 |
| 0.3977 | 22.64 | 2400 | 0.4269 | 0.1477 |
| 0.4098 | 23.58 | 2500 | 0.4384 | 0.1372 |
| 0.3691 | 24.53 | 2600 | 0.4624 | 0.1222 |
| 0.3658 | 25.47 | 2700 | 0.4505 | 0.1233 |
| 0.3415 | 26.42 | 2800 | 0.4620 | 0.1080 |
| 0.3346 | 27.36 | 2900 | 0.4800 | 0.1033 |
| 0.3391 | 28.3 | 3000 | 0.4504 | 0.1014 |
| 0.3223 | 29.25 | 3100 | 0.4284 | 0.0988 |
| 0.3304 | 30.19 | 3200 | 0.4091 | 0.0920 |
| 0.3314 | 31.13 | 3300 | 0.4215 | 0.0889 |
| 0.2913 | 32.08 | 3400 | 0.4317 | 0.0985 |
| 0.3245 | 33.02 | 3500 | 0.4299 | 0.0904 |
| 0.3174 | 33.96 | 3600 | 0.4423 | 0.0877 |
| 0.3083 | 34.91 | 3700 | 0.4288 | 0.0891 |
| 0.314 | 35.85 | 3800 | 0.4262 | 0.0911 |
| 0.3049 | 36.79 | 3900 | 0.4296 | 0.0983 |
| 0.318 | 37.74 | 4000 | 0.4243 | 0.0960 |
| 0.3181 | 38.68 | 4100 | 0.4412 | 0.0990 |
| 0.2923 | 39.62 | 4200 | 0.4288 | 0.1020 |
| 0.3067 | 40.57 | 4300 | 0.4205 | 0.0948 |
| 0.3172 | 41.51 | 4400 | 0.4365 | 0.0966 |
| 0.3394 | 42.45 | 4500 | 0.4153 | 0.0978 |
| 0.2874 | 43.4 | 4600 | 0.4197 | 0.0906 |
| 0.2597 | 44.34 | 4700 | 0.4295 | 0.0987 |
| 0.2713 | 45.28 | 4800 | 0.4456 | 0.0958 |
| 0.2732 | 46.23 | 4900 | 0.4507 | 0.0985 |
| 0.2889 | 47.17 | 5000 | 0.4402 | 0.1042 |
| 0.2538 | 48.11 | 5100 | 0.4275 | 0.0945 |
| 0.2604 | 49.06 | 5200 | 0.4398 | 0.1058 |
| 0.2415 | 50.0 | 5300 | 0.4156 | 0.0959 |
| 0.2414 | 50.94 | 5400 | 0.4254 | 0.0918 |
| 0.2458 | 51.89 | 5500 | 0.4259 | 0.0910 |
| 0.2472 | 52.83 | 5600 | 0.4415 | 0.0925 |
| 0.242 | 53.77 | 5700 | 0.4306 | 0.0873 |
| 0.213 | 54.72 | 5800 | 0.4325 | 0.0887 |
| 0.2172 | 55.66 | 5900 | 0.4139 | 0.0936 |
| 0.2099 | 56.6 | 6000 | 0.4337 | 0.0927 |
| 0.2138 | 57.55 | 6100 | 0.4161 | 0.0862 |
| 0.1992 | 58.49 | 6200 | 0.4117 | 0.0866 |
| 0.2072 | 59.43 | 6300 | 0.4109 | 0.0890 |
| 0.196 | 60.38 | 6400 | 0.4038 | 0.0858 |
| 0.2132 | 61.32 | 6500 | 0.4137 | 0.0885 |
| 0.2067 | 62.26 | 6600 | 0.4068 | 0.0842 |
| 0.2051 | 63.21 | 6700 | 0.3938 | 0.0852 |
| 0.2023 | 64.15 | 6800 | 0.3950 | 0.0878 |
| 0.2025 | 65.09 | 6900 | 0.4008 | 0.0932 |
| 0.2038 | 66.04 | 7000 | 0.4027 | 0.0884 |
| 0.1906 | 66.98 | 7100 | 0.3984 | 0.0868 |
| 0.1927 | 67.92 | 7200 | 0.4045 | 0.0889 |
| 0.2153 | 68.87 | 7300 | 0.4031 | 0.0880 |
| 0.1913 | 69.81 | 7400 | 0.4053 | 0.0873 |
| 0.1795 | 70.75 | 7500 | 0.4024 | 0.0846 |
| 0.1754 | 71.7 | 7600 | 0.4085 | 0.0884 |
| 0.1736 | 72.64 | 7700 | 0.4046 | 0.0863 |
| 0.1738 | 73.58 | 7800 | 0.4012 | 0.0861 |
| 0.1636 | 74.53 | 7900 | 0.4002 | 0.0814 |
| 0.1729 | 75.47 | 8000 | 0.4007 | 0.0802 |
| 0.1809 | 76.42 | 8100 | 0.4055 | 0.0785 |
| 0.1793 | 77.36 | 8200 | 0.4088 | 0.0825 |
| 0.1686 | 78.3 | 8300 | 0.4063 | 0.0841 |
| 0.2006 | 79.25 | 8400 | 0.4056 | 0.0826 |
| 0.1705 | 80.19 | 8500 | 0.4009 | 0.0820 |
| 0.1743 | 81.13 | 8600 | 0.4018 | 0.0799 |
| 0.1797 | 82.08 | 8700 | 0.4015 | 0.0797 |
| 0.1563 | 83.02 | 8800 | 0.3974 | 0.0824 |
| 0.1618 | 83.96 | 8900 | 0.3989 | 0.0797 |
| 0.1615 | 84.91 | 9000 | 0.3970 | 0.0816 |
| 0.1701 | 85.85 | 9100 | 0.3956 | 0.0822 |
| 0.1635 | 86.79 | 9200 | 0.3961 | 0.0784 |
| 0.1674 | 87.74 | 9300 | 0.3953 | 0.0812 |
| 0.1669 | 88.68 | 9400 | 0.3949 | 0.0805 |
| 0.1644 | 89.62 | 9500 | 0.3939 | 0.0812 |
| 0.1672 | 90.57 | 9600 | 0.3930 | 0.0818 |
| 0.169 | 91.51 | 9700 | 0.3936 | 0.0821 |
| 0.1813 | 92.45 | 9800 | 0.3942 | 0.0828 |
| 0.1638 | 93.4 | 9900 | 0.3933 | 0.0813 |
| 0.1561 | 94.34 | 10000 | 0.3947 | 0.0817 |
| 0.1755 | 95.28 | 10100 | 0.3943 | 0.0813 |
| 0.1705 | 96.23 | 10200 | 0.3939 | 0.0810 |
| 0.1826 | 97.17 | 10300 | 0.3937 | 0.0812 |
| 0.1761 | 98.11 | 10400 | 0.3937 | 0.0810 |
| 0.154 | 99.06 | 10500 | 0.3934 | 0.0814 |
| 0.1757 | 100.0 | 10600 | 0.3934 | 0.0812 |