speaker-segmentation-fine-tuned-testESLO28.04.25 – AI Model by Rziane | AlphaNeural AI

You can deploy this model and start earning money today!

Rziane/
speaker-segmentation-fine-tuned-testESLO28.04.25

like

0

speaker-diarization

speaker-segmentation

generated_from_trainer

pyannote/segmentation-3.0

endpoints_compatible

Views

No views yet

speaker-segmentation-fine-tuned-testESLO28.04.25

This model is a fine-tuned version of pyannote/segmentation-3.0 on the ESLO dataset. It achieves the following results on the evaluation set:

Loss: 0.8138
Model Preparation Time: 0.0045
Der: 0.5094
False Alarm: 0.1774
Missed Detection: 0.2335
Confusion: 0.0985

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
0.844	1.0	300	0.8725	0.0045	0.5486	0.1957	0.2335	0.1194
0.7916	2.0	600	0.8553	0.0045	0.5364	0.1660	0.2702	0.1001
0.7781	3.0	900	0.8353	0.0045	0.5207	0.1773	0.2407	0.1028
0.7781	4.0	1200	0.8332	0.0045	0.5201	0.1821	0.2355	0.1024
0.7498	5.0	1500	0.8215	0.0045	0.5119	0.1859	0.2211	0.1049
0.759	6.0	1800	0.8238	0.0045	0.5179	0.1755	0.2428	0.0996
0.7531	7.0	2100	0.8164	0.0045	0.5109	0.1748	0.2355	0.1007
0.7327	8.0	2400	0.8203	0.0045	0.5093	0.1778	0.2314	0.1002
0.7452	9.0	2700	0.8123	0.0045	0.5076	0.1740	0.2372	0.0964
0.6994	10.0	3000	0.8138	0.0045	0.5094	0.1774	0.2335	0.0985

Framework versions

Transformers 4.45.2
Pytorch 2.4.1+cu121
Datasets 3.0.1
Tokenizers 0.20.0