Downloads · 30 days
39
30% of all-time downloads
speaker-segmentation-fine-tuned
sujalappa/speaker-segmentation-fine-tuned
speaker-segmentation-fine-tuned is a machine learning model from sujalappa. 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
131
Public
Parameters
1.5M
5.9 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
- Sep 22, 2025
- Updated
- Sep 22, 2025
- SHA
- 97e46723
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. -->
speaker-diarization-fine-tuned
This model is a fine-tuned version of pyannote/speaker-diarization-3.1 on the sujalappa/temp-speaker-diarization-synthetic-dataset dataset. It achieves the following results on the evaluation set:
- Loss: 0.0626
- Model Preparation Time: 0.0071
- Der: 0.0334
- False Alarm: 0.0059
- Missed Detection: 0.0120
- Confusion: 0.0155
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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Der | False Alarm | Missed Detection | Confusion |
|---|---|---|---|---|---|---|---|---|
| 0.086 | 1.0 | 42 | 0.0856 | 0.0071 | 0.0517 | 0.0105 | 0.0207 | 0.0206 |
| 0.0417 | 2.0 | 84 | 0.0677 | 0.0071 | 0.0415 | 0.0079 | 0.0153 | 0.0183 |
| 0.0278 | 3.0 | 126 | 0.0653 | 0.0071 | 0.0368 | 0.0065 | 0.0132 | 0.0171 |
| 0.0222 | 4.0 | 168 | 0.0638 | 0.0071 | 0.0340 | 0.0058 | 0.0120 | 0.0162 |
| 0.0242 | 5.0 | 210 | 0.0626 | 0.0071 | 0.0334 | 0.0059 | 0.0120 | 0.0155 |
Framework versions
- Transformers 4.56.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.0
- Library
- transformers
- Type
- pyannet
- License
- mit
- Created
- Sep 22, 2025
- Updated
- Sep 22, 2025