Downloads · 30 days
6
4% of all-time downloads
dianavdavidson/whisper-medium_vaani_62419_ratio_alldata_lr_1e-4_lgid_None_epochs_100_FT
whisper-medium_vaani_62419_ratio_alldata_lr_1e-4_lgid_None_epochs_100_FT is a automatic speech recognition model from dianavdavidson. 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
6
4% of all-time downloads
All-time downloads
141
Public
Parameters
764M
27.5 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 an unknown 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 | Global Wer |
|---|---|---|---|---|
| 1.3699 | 1.0 | 540 | 0.5793 | 19.2449 |
| 0.8679 | 2.0 | 1080 | 0.5571 | 28.5848 |
| 0.5547 | 3.0 | 1620 | 0.5797 | 14.9678 |
| 0.4193 | 4.0 | 2160 | 0.5732 | 15.7125 |
| 0.3158 | 5.0 | 2700 | 0.6068 | 14.9753 |
| 0.2542 | 6.0 | 3240 | 0.6258 | 13.6881 |
| 0.2126 | 7.0 | 3780 | 0.6418 | 14.7246 |
| 0.1859 | 8.0 | 4320 | 0.7007 | 16.3898 |
| 0.1627 | 9.0 | 4860 | 0.6894 | 16.6779 |