Downloads · 30 days
3
5% of all-time downloads
crisperwhisper-mhdp-english
sulaimank/crisperwhisper-mhdp-english
crisperwhisper-mhdp-english is a machine learning model from sulaimank. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as cc-by-nc-4.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
63
Public
Parameters
1.5B
12.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6.2 GB · 100%
At a glance
- License
- cc-by-nc-4.0
- Model type
- whisper
- Access
- Public
- Created
- Jun 1, 2026
- Updated
- Jun 2, 2026
- SHA
- f13a1a31
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
crisperwhisper-mhdp-english
This model is a fine-tuned version of nyrahealth/CrisperWhisper on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1205
- Wer: 0.0780
- Cer: 0.0547
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 4
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 0.4398 | 1.0 | 1598 | 0.0818 | 0.0878 | 0.0698 |
| 0.1279 | 2.0 | 3197 | 0.0711 | 0.0863 | 0.0658 |
| 0.0925 | 3.0 | 4796 | 0.0805 | 0.0837 | 0.0628 |
| 0.0685 | 4.0 | 6395 | 0.0855 | 0.0783 | 0.0557 |
| 0.0465 | 5.0 | 7993 | 0.0813 | 0.0811 | 0.0614 |
| 0.031 | 6.0 | 9592 | 0.0925 | 0.0940 | 0.0721 |
| 0.0217 | 7.0 | 11191 | 0.1017 | 0.0816 | 0.0577 |
| 0.0154 | 8.0 | 12790 | 0.1025 | 0.0747 | 0.0530 |
| 0.0116 | 9.0 | 14388 | 0.1068 | 0.0780 | 0.0540 |
| 0.0093 | 10.0 | 15987 | 0.1087 | 0.0842 | 0.0593 |
| 0.0072 | 11.0 | 17586 | 0.1167 | 0.0780 | 0.0537 |
| 0.0057 | 12.0 | 19185 | 0.1219 | 0.0801 | 0.0549 |
| 0.0054 | 13.0 | 20783 | 0.1205 | 0.0780 | 0.0547 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.8.0.dev20250319+cu128
- Datasets 3.6.0
- Tokenizers 0.15.2
- Type
- whisper
- License
- cc-by-nc-4.0
- Created
- Jun 1, 2026
- Updated
- Jun 2, 2026