thomas.gossin

Hello, My goal would be to get the embedding of each Speaker from the diarization in order to do some identification afterwards. I checked the code to add this feature...

Inconsistent Inference Speed vs GPU Utilization with Batch Size Variation in pyannote Audio Models

4

# Hello, I'm currently working with pyannote/speaker-diarization-3.1 for embedding, specifically using pyannote/wespeaker-voxceleb-resnet34-LM. I've been experimenting with different batch sizes (32, 64, 128) to optimize performance. To better understand the performance,...

Error using assign method with IndexBinary in FAISS

1

### Description: I am encountering an issue when attempting to use the `assign` method on an `IndexBinary` object in FAISS. The objective is to assign each input vector to the...

User/tgossin/2025 05 25 merge dataset

9

### PR: Add `merge_dataset.py` utility script This PR introduces **`merge_dataset.py`**, a standalone CLI tool to **merge two LeRobot-format datasets into a single, coherent dataset** while guaranteeing that all episode indices...