diart

diart copied to clipboard

service hangs after pressing ctrl+C on the client side

9

How to reproduce: 1, start the server side 2, start the client side 3, press ctrl+C on the client side and restart the client side Then the server side will...

ywangwxd

Support multiple client connections over Websocket

3

Looked at the `WebSocketAudioSource` class to realise that the server will only support one client at a time. Also leads to this weird (but expected, i guess) behaviour - when...

janaab11

Add reset functionality successfully to the streaming process

1

Hello, If you are like me and want to have a reset functionality, I would like to share my experiece here. By reset functionality I mean this effect: 1, start...

ywangwxd

Update matplotlib Requirement

1

The current matplotlib version requirement in diart (matplotlib>=3.3.3,

QuentinFuxa

how to run diariazation pipeline on multiple file segments ?

2

I am trying to run the diariazation pipeline on multiple file segments which are continuous parts of a long audio file. Here is what I am doing. To put it...

ywangwxd

Hi @juanmc2005 How are you? How can I get the embedding as diarization result through your pipe-line too? I posted the same question in your diart_whisper repo (https://gist.github.com/juanmc2005/ed6413e697e176cb36a149d8c40a3a5b).

rose-jinyang

add support of pyannote segmentation 3.0 (experience sharing)

3

Hi, if anyone like me is working on the `feat/diart-asr` branch and want to add support of pyannote segmentation 3.0. Here is what I have done. You only need to...

ywangwxd

Why the sliding windows are so tight in the diariazation process?

3

Luckily, I have integrated faster whisper successfully into the diart-spk branch. Maybe I will submit a PR later. But I have a question about the sliding windows in diariazation. I...

ywangwxd

Is this code being used into the pyannote-audio >= 2.1 ?

4

Based on this [paper](https://www.isca-archive.org/interspeech_2023/bredin23_interspeech.pdf) may I assume that versions of pyannote-audio >= 2.1 are using the diart methodology? For example, if I run this code, will it be executed in...

nikifori

extracting unique speaker embeddings from pipeline

1

have not found a way to extract unique speaker embeddings from the pipeline after running it. it would allow to similarity function against existing saved speaker embeddings to identify speakers.

Aduomas