Downloads · 30 days
18
21% of all-time downloads
daeinbangeu/wav2vec2-large-xls-r-300m-korean-g-TW3
wav2vec2-large-xls-r-300m-korean-g-TW3 is a automatic speech recognition model from daeinbangeu. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
18
21% of all-time downloads
All-time downloads
86
Public
Repo size
20.2 GB
Likes
0
Public
Click a slice to open those files.
.bin1.3 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the None 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 | Cer |
|---|---|---|---|---|
| 4.788 | 3.25 | 500 | 3.5692 | 0.9883 |
| 1.3778 | 6.49 | 1000 | 0.9800 | 0.2359 |
| 0.3789 | 9.74 | 1500 | 0.8269 | 0.1970 |
| 0.2101 | 12.99 | 2000 | 0.9330 | 0.1874 |
| 0.1507 | 16.23 | 2500 | 0.8702 | 0.1733 |
| 0.1208 | 19.48 | 3000 | 0.9377 | 0.1685 |
| 0.1019 | 22.73 | 3500 | 0.8957 | 0.1622 |
| 0.0878 | 25.97 | 4000 | 0.9258 | 0.1595 |
| 0.0772 | 29.22 | 4500 | 0.9001 | 0.1536 |