juanmc2005 / diart

A python package to build AI-powered real-time audio applications

https://diart.readthedocs.io

juanmc2005/diart Issues

Create a Docker image
Updated 15 days ago4
Running diart + Whisper on Raspberry Pi 5
Updated 2 months ago10
Speaker Identity Resolution
Closed 3 months ago2
Minimizing missed detection
Updated 3 months ago7
quality concerns
Updated 3 months ago1
Feature Request: Implementing Persistent Speaker Embeddings Across Conversations
Updated 4 months ago3
The latency of wespeaker model is to large
Updated 5 months ago1
Implement voicefixer for audio enhancement
Updated 5 months ago6
diart vs whisperx diarization accuracy
Closed 5 months ago4
WeSpeaker model load failed!
Closed 5 months ago2
High CPU usage
Closed 5 months ago3
ImportError: cannot import name 'OnlineSpeakerDiarization' from 'diart'
Updated 5 months ago9
No speaker
Closed 6 months ago
Get rid of LazyModel
Updated 6 months ago
Compatibility with pyannote 3.1
Closed 6 months ago1
Optimize weighted embedding extraction with pyannote 3.1
Updated 6 months ago7
Make ONNX an optional dependency
Closed 6 months ago
[joss][docs] - Collected Docs suggestions
Closed 6 months ago3
Improve README
Closed 6 months ago
[joss] Need locations of benchmarking data!
Updated 6 months ago2
Add tutorials to the documentation page
Updated 6 months ago
Add a caching mechanism for benchmark and tuning
Updated 6 months ago
Load pipeline config from yaml file
Updated 6 months ago
[joss] Tests?
Updated 6 months ago5
Adapt "step" automagically
Updated 6 months ago2
Add compatibility with ONNX models
Closed 6 months ago
Running Diart_Whisper on Windows and nothing happens
Updated 6 months ago2
Add compatibility with new pyannote segmentation model
Closed 6 months ago6
Add compatibility with new pyannote embedding models
Closed 6 months ago1
TypeError: forward() got an unexpected keyword argument 'weights'
Closed 6 months ago2
Using with python > 3.8
Closed 6 months ago8
Switch to a faster library for dynamic resampling
Updated 6 months ago1
[joss] Inconsistent naming causes cli arguments to be ignored
Closed 7 months ago3
[joss][ux][minor] Catch `KeyboardInterrupt` in `diart.stream`
Closed 7 months ago1
Issue installing diart on Mac M1 due to hmmlearn error
Closed 7 months ago3
diart.stream microphone fail to work on macos
Closed 7 months ago8
Compatibility errors between Diart requirements and Pyannote
Closed 7 months ago2
Crash when 16khz sampling is not supported by input device
Closed 7 months ago1
Reduce redundancy in dynamic resampling
Updated 7 months ago
Adding realtime diarization to collabora/WhisperLive
Closed 7 months ago
[joss] Outdated torchaudio can't find newer ffmpeg, conda environment.yml file missing to specify version
Closed 7 months ago7
Manual speaker managment to remove duplicates
Closed 8 months ago1
Python Sample is not working in Windows 11
Closed 8 months ago2
Windows 10 - Exits with no errors or results
Updated 8 months ago8
Words repeated in whisper transcription with initial_prompt
Updated 8 months ago7
Client for the websocket server
Closed 10 months ago4
Diart+Whisper for real time transcription not working as expected
Closed 10 months ago2
Slowdown Process when Concurrent Process
Closed 10 months ago5
How would I go on to provide real time transcribing (with diarization), preferrably with whisper (or whisperX)
Closed a year ago1
Does it make coffee?
Closed a year ago1