diart

diart copied to clipboard

Switch to a faster library for dynamic resampling

1

Looks like `torchaudio.Resample` is not very fast compared to other libraries implementing resampling in python. See https://github.com/jonashaag/audio-resampling-in-python Looks like we could switch to `soxr` and get a 10x speed increase.

juanmc2005

In `RealTimeInference`, resample before `rearrange_audio_stream` so the same audio is not resampled multiple times. Because of how the first 5s buffer is filled at the beginning, this actually means that...

juanmc2005

Windows 10 - Exits with no errors or results

8

when I run: diart.stream speakers:9, or execute it in a python script it simply sends a notice about sox_io, and then exits. No errors. How do I figure out what's...

matbeedotcom

Words repeated in whisper transcription with initial_prompt

7

Hello all, Thank you for doing this great work! I just updated this code to use faster whisper and I facing repeated words issue when I use initial_prompt param in...

ahmedmoorsy

## Problem The amount of parallel pipelines that can run in `Benchmark` is limited because the models need to be copied in each process. ## Idea Serve models in a...

juanmc2005

## Problem The implementation of the CLI is a bit messy and mixed with the python API. ## Idea Use [jsonargparse](https://jsonargparse.readthedocs.io/en/stable/) to group `diart.stream`, `diart.tune` and `diart.benchmark` into a single...

juanmc2005

Diarization process with faster-whisper

2

I have a working application with real-time transcription feature based on **faster-whisper**. However, after applying **diart** pipeline to my existing application, I get transcription with no diarization. I expect the...

RustX2802

Fix torch `detach()` before `numpy()` issue

4

Hi @juanmc2005 , This PR is solving the error of complaining torch doesn't have subclass numpy issue. It's just detaching the torch before call numpy(). Please review and let me...

pengwei715

Updated README embed-extraction pipeline example with new sample rate = 16000. Also updated the print to display the embeds and added hf_token parameter. Let me know if you only want...

hmehdi515

Trying to extract embeds

3

Hi, I am trying to run a pipeline to extract embeddings The pipeline I am running is the one in the README: ``` import rx.operators as ops import diart.operators as...

hmehdi515