Downloads · 30 days
14
15% of all-time downloads
agnivamaiti/jem-whisper-yi-2026-09-04-v3-cont
jem-whisper-yi-2026-09-04-v3-cont is a automatic speech recognition model from agnivamaiti. Use it when you need speech turned into text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
14
15% of all-time downloads
All-time downloads
92
Public
Parameters
1.5B
43.2 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors6.2 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of Kohn-AI/jem-whisper-yi-2026-09-03-v3-step3488 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 | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.141 | 0.2866 | 250 | 0.4138 | 0.3013 | 0.2343 |
| 0.1278 | 0.5732 | 500 | 0.4156 | 0.3162 | 0.2563 |
| 0.103 | 0.8598 | 750 | 0.4194 | 0.3119 | 0.2441 |
| 0.0908 | 1.1456 | 1000 | 0.4522 | 0.3342 | 0.2645 |
| 0.0952 | 1.4322 | 1250 | 0.4571 | 0.3034 | 0.2382 |
| 0.1015 | 1.7188 | 1500 | 0.4537 | 0.3105 | 0.2409 |