Downloads · 30 days
8
4% of all-time downloads
Sonhy/whisper-medium-korean-kspon-1
whisper-medium-korean-kspon-1 is a automatic speech recognition model from Sonhy. 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
4% of all-time downloads
All-time downloads
212
Public
Parameters
764M
6.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors3.1 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of openai/whisper-medium on the ksponspeech 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 |
|---|---|---|---|---|
| 0.3254 | 1.187 | 500 | 0.4439 | 28.3596 |
| 0.1111 | 3.061 | 1000 | 0.4098 | 25.8758 |