speaker-segmentation-fine-tuned-callhome-hi
This model is a fine-tuned version of pyannote/speaker-diarization-3.1 on the diarizers-community/callhome dataset. It achieves the following results on the evaluation set:
- Loss: 0.4388
- Der: 0.1470
- False Alarm: 0.0241
- Missed Detection: 0.0294
- Confusion: 0.0934
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 adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Der | False Alarm | Missed Detection | Confusion |
|---|---|---|---|---|---|---|---|
| 0.4572 | 1.0 | 194 | 0.4811 | 0.1598 | 0.0239 | 0.0319 | 0.1041 |
| 0.3809 | 2.0 | 388 | 0.4470 | 0.1488 | 0.0223 | 0.0315 | 0.0950 |
| 0.3892 | 3.0 | 582 | 0.4388 | 0.1470 | 0.0241 | 0.0294 | 0.0934 |
Framework versions
- Transformers 4.48.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 4
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model’s pipeline type.
Model tree for abhimehra8194/speaker-segmentation-fine-tuned-callhome-hindi-2
Base model
pyannote/speaker-diarization-3.1