Downloads · 30 days
4
8% of all-time downloads
speaker-segmentation-fine-tuned-CAENNAIS-v3
Rziane/speaker-segmentation-fine-tuned-CAENNAIS-v3
speaker-segmentation-fine-tuned-CAENNAIS-v3 is a machine learning model from Rziane. 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 transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
52
Public
Parameters
1.5M
59.1 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors5.9 MB · 100%
At a glance
- Library
- transformers
- License
- mit
- Model type
- pyannet
- Access
- Public
- Created
- Mar 12, 2025
- Updated
- Mar 12, 2025
- SHA
- 4645edac
Base models
Datasets
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. -->
speaker-segmentation-fine-tuned_CAENNAIS
This model is a fine-tuned version of pyannote/segmentation-3.0 on the CAENNAIS dataset. It achieves the following results on the evaluation set:
- Loss: 0.7201
- Model Preparation Time: 0.0037
- Der: 0.3164
- False Alarm: 0.1145
- Missed Detection: 0.0684
- Confusion: 0.1335
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: 0.001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Der | False Alarm | Missed Detection | Confusion |
|---|---|---|---|---|---|---|---|---|
| 0.8687 | 1.0 | 61 | 0.8189 | 0.0037 | 0.3927 | 0.1128 | 0.0900 | 0.1899 |
| 0.7991 | 2.0 | 122 | 0.7751 | 0.0037 | 0.3552 | 0.1158 | 0.0750 | 0.1644 |
| 0.7269 | 3.0 | 183 | 0.7795 | 0.0037 | 0.3571 | 0.1269 | 0.0622 | 0.1680 |
| 0.6891 | 4.0 | 244 | 0.7384 | 0.0037 | 0.3360 | 0.1233 | 0.0642 | 0.1485 |
| 0.6723 | 5.0 | 305 | 0.7053 | 0.0037 | 0.3235 | 0.1017 | 0.0807 | 0.1411 |
| 0.6409 | 6.0 | 366 | 0.7068 | 0.0037 | 0.3193 | 0.1142 | 0.0680 | 0.1372 |
| 0.6345 | 7.0 | 427 | 0.7200 | 0.0037 | 0.3243 | 0.1150 | 0.0695 | 0.1398 |
| 0.6087 | 8.0 | 488 | 0.7483 | 0.0037 | 0.3302 | 0.1241 | 0.0623 | 0.1438 |
| 0.5997 | 9.0 | 549 | 0.7163 | 0.0037 | 0.3158 | 0.1139 | 0.0689 | 0.1330 |
| 0.5976 | 10.0 | 610 | 0.7201 | 0.0037 | 0.3164 | 0.1145 | 0.0684 | 0.1335 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.0
- Library
- transformers
- Type
- pyannet
- License
- mit
- Languages
- fr
- Created
- Mar 12, 2025
- Updated
- Mar 12, 2025