Hugging Face's logo

Rziane
/
model.no2_expe.dia.1.A_data_ESLO_06.05.25

Transformers
PyTorch
TensorBoard
Safetensors
French
pyannet
speaker-diarization
speaker-segmentation
Generated from Trainer
Model card Files Metrics Community
model.no2_expe.dia.1.A_data_ESLO_06.05.25 / README.md
Rziane's picture
Rziane
End of training
4179cd2 verified
preview code
|
raw
history blame contribute delete
4.28 kB
metadata
library_name: transformers
language:
  - fr
license: mit
base_model: pyannote/segmentation-3.0
tags:
  - speaker-diarization
  - speaker-segmentation
  - generated_from_trainer
datasets:
  - CAENNAIS
model-index:
  - name: model.no2_expe.dia.1.A_data_ESLO_06.05.25
    results: []

model.no2_expe.dia.1.A_data_ESLO_06.05.25

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: 0.7552
  • Model Preparation Time: 0.0039
  • Der: 0.4612
  • False Alarm: 0.1526
  • Missed Detection: 0.2132
  • Confusion: 0.0953

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: 20

Training results

Training Loss Epoch Step Validation Loss Model Preparation Time Der False Alarm Missed Detection Confusion
0.8598 1.0 270 0.8043 0.0039 0.5158 0.1643 0.2233 0.1282
0.8108 2.0 540 0.7766 0.0039 0.4948 0.1529 0.2280 0.1139
0.795 3.0 810 0.7713 0.0039 0.4886 0.1697 0.1979 0.1210
0.7601 4.0 1080 0.7588 0.0039 0.4746 0.1590 0.2119 0.1037
0.7705 5.0 1350 0.7490 0.0039 0.4675 0.1374 0.2429 0.0871
0.7667 6.0 1620 0.7848 0.0039 0.4784 0.1537 0.2247 0.1000
0.7198 7.0 1890 0.7692 0.0039 0.4855 0.1353 0.2505 0.0996
0.7266 8.0 2160 0.7474 0.0039 0.4671 0.1448 0.2267 0.0955
0.7011 9.0 2430 0.7509 0.0039 0.4622 0.1675 0.1915 0.1032
0.717 10.0 2700 0.7523 0.0039 0.4656 0.1578 0.2123 0.0955
0.7083 11.0 2970 0.7439 0.0039 0.4624 0.1443 0.2320 0.0861
0.7153 12.0 3240 0.7462 0.0039 0.4614 0.1548 0.2091 0.0975
0.6498 13.0 3510 0.7512 0.0039 0.4663 0.1564 0.2122 0.0978
0.6935 14.0 3780 0.7501 0.0039 0.4621 0.1533 0.2139 0.0950
0.6746 15.0 4050 0.7534 0.0039 0.4632 0.1544 0.2139 0.0950
0.6751 16.0 4320 0.7515 0.0039 0.4627 0.1552 0.2122 0.0952
0.6848 17.0 4590 0.7542 0.0039 0.4632 0.1516 0.2187 0.0928
0.6759 18.0 4860 0.7577 0.0039 0.4605 0.1534 0.2121 0.0951
0.6856 19.0 5130 0.7540 0.0039 0.4609 0.1525 0.2135 0.0949
0.7036 20.0 5400 0.7552 0.0039 0.4612 0.1526 0.2132 0.0953

Framework versions

  • Transformers 4.45.2
  • Pytorch 2.4.1+cu121
  • Datasets 3.0.1
  • Tokenizers 0.20.0