Downloads · 30 days
6
6% of all-time downloads
dianavdavidson/whisper-medium_vaani_62419_ratio_alldata_lr_1e-4_lgid_en_epochs_100_FT
whisper-medium_vaani_62419_ratio_alldata_lr_1e-4_lgid_en_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
6% of all-time downloads
All-time downloads
105
Public
Parameters
764M
21.4 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 |
|---|---|---|---|---|
| 0.9465 | 1.0 | 540 | 0.5390 | 17.0932 |
| 0.7935 | 2.0 | 1080 | 0.5177 | 15.8696 |
| 0.5058 | 3.0 | 1620 | 0.5168 | 14.5787 |
| 0.3735 | 4.0 | 2160 | 0.5381 | 13.3026 |
| 0.2834 | 5.0 | 2700 | 0.5591 | 16.1091 |
| 0.2428 | 6.0 | 3240 | 0.5698 | 14.8967 |
| 0.1925 | 7.0 | 3780 | 0.6006 | 15.2672 |