Downloads · 30 days
12
13% of all-time downloads
emre/wav2vec2-xls-r-300m-Turkish-Tr-med
wav2vec2-xls-r-300m-Turkish-Tr-med is a automatic speech recognition model from emre. 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
12
13% of all-time downloads
All-time downloads
92
Public
Repo size
3.8 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 common_voice 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 |
|---|---|---|---|---|
| 4.8093 | 4.21 | 400 | 2.7831 | 1.0 |
| 0.9881 | 8.42 | 800 | 0.5088 | 0.6681 |
| 0.3519 | 12.63 | 1200 | 0.4496 | 0.6007 |
| 0.2436 | 16.84 | 1600 | 0.4993 | 0.5654 |
| 0.1874 | 21.05 | 2000 | 0.4793 | 0.5530 |
| 0.1561 | 25.26 | 2400 | 0.5187 | 0.5589 |
| 0.1336 | 29.47 | 2800 | 0.5135 | 0.5311 |
| 0.1163 | 33.68 | 3200 | 0.4960 | 0.5143 |
| 0.1056 | 37.89 | 3600 | 0.4795 | 0.5045 |
| 0.0959 | 42.11 | 4000 | 0.4883 | 0.4987 |
| 0.0819 | 46.32 | 4400 | 0.4799 | 0.4903 |
| 0.0756 | 50.53 | 4800 | 0.4822 | 0.4831 |
| 0.0692 | 54.74 | 5200 | 0.4621 | 0.4762 |
| 0.062 | 58.95 | 5600 | 0.4727 | 0.4677 |