Downloads · 30 days
6
21% of all-time downloads
full-whisper-Franko-CS-v0-transcribe
Moamen-dcp/full-whisper-Franko-CS-v0-transcribe
full-whisper-Franko-CS-v0-transcribe is a machine learning model from Moamen-dcp. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
28
Public
Repo size
210 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors52.5 MB · 100%
At a glance
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Jun 9, 2025
- Updated
- Jun 9, 2025
- SHA
- 28418a06
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. -->
full-whisper-Franko-CS-v0-transcribe
This model is a fine-tuned version of openai/whisper-large-v3-turbo on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5593
- Wer: 36.4135
- Wer Normalized: 25.5190
- Cer: 15.4281
- Cer Normalized: 11.8079
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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Wer Normalized | Cer | Cer Normalized |
|---|---|---|---|---|---|---|---|
| 0.8306 | 1.4354 | 300 | 0.9119 | 54.4801 | 43.5926 | 30.1381 | 24.7459 |
| 0.4817 | 2.8708 | 600 | 0.5867 | 37.9260 | 27.0768 | 16.1407 | 12.5671 |
| 0.4008 | 4.3062 | 900 | 0.5593 | 36.4135 | 25.5190 | 15.4281 | 11.8079 |
Framework versions
- PEFT 0.15.2
- Transformers 4.52.4
- Pytorch 2.7.1+cu128
- Datasets 3.6.0
- Tokenizers 0.21.1
- Library
- peft
- License
- mit
- Created
- Jun 9, 2025
- Updated
- Jun 9, 2025