You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

speaker-segmentation-fine-tuned-MHDP-butabika-diarization-v1

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

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 0.001
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
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: 50

Training Loss	Epoch	Step	Validation Loss	Der	False Alarm	Missed Detection	Confusion
0.8163	1.0	395	0.7955	0.2492	0.2192	0.0299	0.0
0.8011	2.0	790	0.8111	0.2601	0.2001	0.0600	0.0001
0.7162	3.0	1185	0.7964	0.2558	0.1988	0.0569	0.0001
0.6934	4.0	1580	0.8639	0.2855	0.1407	0.1432	0.0015
0.6577	5.0	1975	0.8951	0.2980	0.1325	0.1640	0.0015
0.604	6.0	2370	0.8524	0.2763	0.1558	0.1193	0.0012

Safetensors

Model size

1.47M params

Tensor type

F32

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Base model

Finetuned

(95)

this model