Downloads · 30 days
41
6% of all-time downloads
infinitejoy/wav2vec2-large-xls-r-300m-georgian
wav2vec2-large-xls-r-300m-georgian is a automatic speech recognition model from infinitejoy. 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
41
6% of all-time downloads
All-time downloads
726
Public
Repo size
22.7 GB
Likes
1
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 MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - KA 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 |
|---|---|---|---|---|
| 1.8805 | 5.95 | 500 | 0.7547 | 0.8438 |
| 1.2123 | 11.9 | 1000 | 0.4732 | 0.6542 |
| 1.0822 | 17.86 | 1500 | 0.4027 | 0.5778 |
| 0.9938 | 23.81 | 2000 | 0.3847 | 0.5524 |
| 0.9383 | 29.76 | 2500 | 0.3845 | 0.5204 |
| 0.8932 | 35.71 | 3000 | 0.3833 | 0.5297 |
| 0.8495 | 41.67 | 3500 | 0.3759 | 0.5036 |
| 0.8201 | 47.62 | 4000 | 0.3616 | 0.4859 |
| 0.7794 | 53.57 | 4500 | 0.3874 | 0.4938 |
| 0.735 | 59.52 | 5000 | 0.3748 | 0.4782 |
| 0.7082 | 65.48 | 5500 | 0.3615 | 0.4675 |
| 0.669 | 71.43 | 6000 | 0.3797 | 0.4601 |
| 0.6457 | 77.38 | 6500 | 0.3812 | 0.4515 |
| 0.6098 | 83.33 | 7000 | 0.3660 | 0.4343 |
| 0.5874 | 89.29 | 7500 | 0.3640 | 0.4257 |
| 0.5627 | 95.24 | 8000 | 0.3661 | 0.4239 |