metadata

license: cc-by-4.0
language:
  - es
base_model:
  - pyannote/segmentation-3.0
library_name: pyannote-audio

pyannote-segmentation-3.0-RTVE

Model Details

This model is a fine-tuned version of pyannote/segmentation-3.0 on the RTVE database used for Albayzin Evaluations of IberSPEECH 2024.

On the RTVE2024 test set it achives the following results (two-decimal rounding):

Diarization Error Rate (DER): 15.19%
False Alarm: 2.74%
Missed Detection: 4.55%
Speaker Confusion: 7.90%

Uses

This fine-tuned segmentation model is intented to be used for speaker diarization of TV shows.

Training Details

Training Data

The train.lst file includes the URIs of the training data.

Training Hyperparameters

Model:

duration: 10.0
max_speakers_per_chunk: 3
max_speakers_per_frame: 2
train_batch_size: 32
powerset_max_classes: 2

Adam Optimizer:

lr: 0.0001

Early Stopping:

monitor: 'DiarizationErrorRate'
direction: 'min'
max_epochs: 20

Development Data

The development.lst file includes the URIs of the development data.

Evaluation

Forgiveness collar: 250ms
Skip overlap: False

Testing Data & Metrics

Testing Data

The test.lst file includes the URIs of the testing data.

Metrics

Diarization Error Rate, False Alarm, Missed Detection, Speaker Confusion.

Citation

If you use this model, please cite:

BibTeX:

@inproceedings{souganidis24_iberspeech,
  title     = {HiTZ-Aholab Speaker Diarization System for Albayzin Evaluations of IberSPEECH 2024},
  author    = {Christoforos Souganidis and Gemma Meseguer and Asier Herranz and Inma {Hernáez Rioja} and Eva Navas and Ibon Saratxaga},
  year      = {2024},
  booktitle = {IberSPEECH 2024},
  pages     = {327--330},
  doi       = {10.21437/IberSPEECH.2024-68},
}