Downloads · 30 days
8
1% of all-time downloads
inseong00/wav2vec2-large-xlsr-korean-autumn
wav2vec2-large-xlsr-korean-autumn is a automatic speech recognition model from inseong00. 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
8
1% of all-time downloads
All-time downloads
980
Public
Parameters
317M
1.3 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors1.3 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of kresnik/wav2vec2-large-xlsr-korean 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 | Wer |
|---|---|---|---|---|
| 3.1585 | 1.3077 | 5 | 2.2519 | 0.7065 |
| 1.865 | 2.6154 | 10 | 1.1961 | 0.4886 |
| 1.2524 | 3.9231 | 15 | 0.9087 | 0.3840 |
| 0.8224 | 5.0 | 20 | 0.7890 | 0.3473 |
| 0.8764 | 6.3077 | 25 | 0.7040 | 0.3248 |
| 0.7852 | 7.6154 | 30 | 0.6546 | 0.2961 |
| 0.7128 | 8.9231 | 35 | 0.6356 | 0.2902 |
| 0.5602 | 10.0 | 40 | 0.6111 | 0.2839 |
| 0.6499 | 11.3077 | 45 | 0.5964 | 0.2797 |
| 0.6258 | 12.6154 | 50 | 0.5944 | 0.2761 |
| 0.6306 | 13.9231 | 55 | 0.5916 | 0.2778 |
| 0.5278 | 15.0 | 60 | 0.5920 | 0.2792 |