Downloads · 30 days
34
4% of all-time downloads
Padomin/t5-base-TEDxJP-0front-1body-1rear
t5-base-TEDxJP-0front-1body-1rear is a machine learning model from Padomin. 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-sa-4.0.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
34
4% of all-time downloads
All-time downloads
837
Public
Repo size
36.6 GB
Likes
0
Public
Click a slice to open those files.
.bin892 MB · 100%
From the Hugging Face model README
This model is a fine-tuned version of sonoisa/t5-base-japanese on the te_dx_jp 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 | Mer | Wil | Wip | Hits | Substitutions | Deletions | Insertions | Cer |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.6609 | 1.0 | 1457 | 0.5121 | 0.2181 | 0.2049 | 0.2958 | 0.7042 | 54651 | 6867 | 3069 | 4151 | 0.1880 |
| 0.5633 | 2.0 | 2914 | 0.4719 | 0.1891 | 0.1817 | 0.2714 | 0.7286 | 55015 | 6654 | 2918 | 2644 | 0.1558 |
| 0.5212 | 3.0 | 4371 | 0.4626 | 0.1838 | 0.1771 | 0.2666 | 0.7334 | 55168 | 6635 | 2784 | 2452 | 0.1462 |
| 0.4498 | 4.0 | 5828 | 0.4616 | 0.1807 | 0.1747 | 0.2643 | 0.7357 | 55148 | 6630 | 2809 | 2231 | 0.1420 |
| 0.4058 | 5.0 | 7285 | 0.4633 | 0.1799 | 0.1739 | 0.2631 | 0.7369 | 55200 | 6592 | 2795 | 2231 | 0.1419 |
| 0.3802 | 6.0 | 8742 | 0.4675 | 0.1796 | 0.1733 | 0.2630 | 0.7370 | 55311 | 6636 | 2640 | 2321 | 0.1412 |
| 0.4126 | 7.0 | 10199 | 0.4737 | 0.1781 | 0.1724 | 0.2617 | 0.7383 | 55245 | 6595 | 2747 | 2163 | 0.1394 |
| 0.3436 | 8.0 | 11656 | 0.4772 | 0.1788 | 0.1729 | 0.2624 | 0.7376 | 55247 | 6616 | 2724 | 2208 | 0.1401 |
| 0.3249 | 9.0 | 13113 | 0.4827 | 0.1796 | 0.1735 | 0.2632 | 0.7368 | 55265 | 6635 | 2687 | 2281 | 0.1407 |
| 0.3347 | 10.0 | 14570 | 0.4869 | 0.1801 | 0.1739 | 0.2635 | 0.7365 | 55253 | 6626 | 2708 | 2296 | 0.1411 |