Downloads · 30 days
11
11% of all-time downloads
speaker-segmentation-bengali-optimized-cfg-1-balanced
lucius-40/speaker-segmentation-bengali-optimized-cfg-1-balanced
speaker-segmentation-bengali-optimized-cfg-1-balanced is a machine learning model from lucius-40. 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
100
Public
Parameters
1.5M
23.6 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
- Feb 10, 2026
- Updated
- Feb 10, 2026
- SHA
- 8d7083c5
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-bengali-optimized-cfg-1-balanced
This model is a fine-tuned version of pyannote/segmentation-3.0 on the bengali-speaker-diarization dataset. It achieves the following results on the evaluation set:
- Loss: 0.5044
- Model Preparation Time: 0.0047
- Der: 0.1644
- False Alarm: 0.0427
- Missed Detection: 0.0190
- Confusion: 0.1027
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: 0.0008
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.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_ratio: 0.15
- num_epochs: 12
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Der | False Alarm | Missed Detection | Confusion |
|---|---|---|---|---|---|---|---|---|
| 0.4006 | 1.0 | 254 | 0.4589 | 0.0047 | 0.1579 | 0.0356 | 0.0229 | 0.0994 |
| 0.376 | 2.0 | 508 | 0.4763 | 0.0047 | 0.1666 | 0.0374 | 0.0277 | 0.1015 |
| 0.4243 | 3.0 | 762 | 0.4655 | 0.0047 | 0.1580 | 0.0365 | 0.0253 | 0.0962 |
| 0.3287 | 4.0 | 1016 | 0.5044 | 0.0047 | 0.1644 | 0.0427 | 0.0190 | 0.1027 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.8.0+cu126
- Datasets 3.6.0
- Tokenizers 0.21.4
- Library
- transformers
- Type
- pyannet
- License
- mit
- Languages
- bn
- Created
- Feb 10, 2026
- Updated
- Feb 10, 2026