diart
diart copied to clipboard
A python package to build AI-powered real-time audio applications
## Problem When writing custom models or pipelines, one may want to react to specific inference events, for example before/after benchmarking on a file. ## Idea Add classes `RealTimeInferenceHook` and...
hi @juanmc2005 it's me again, trouble maker QAQ I have a problem when using "diart.stream microphone" in the conda env "diart" i follow the install step  when I connect...
This PR addresses issue #96 and introduces a new feature for custom pipelines. ## Changelog - Add `BasePipelineConfig` and `BasePipeline` as minimal interfaces to respect for custom pipelines - A...
## Problem It's getting increasingly difficult to add features and make sure nothing's broken. ## Idea A suite of automated tests would be great to verify that everything's ok before...
`diart.tune --tau ... --rho ... --delta ...` doesn't seem to use the values provided for the first iteration
## Problem It could be useful to enroll speakers to kickstart the pipeline with precomputed centroids. ## Idea Add a method `enroll(centroids)` to `OnlineSpeakerDiarization` and `OnlineSpeakerClustering`. ## Example ```python import...
## Problem Running a benchmark on a huge dataset can take a lot of time. One of the main bottlenecks is that files are processed sequentially. ## Idea Make `diart.benchmark`...
## Problem Installation requires multiple steps, which were necessary when pyannote.audio 2.0 hadn't been released. Now that this isn't needed anymore, it would be better to simplify the steps for...
following to Feature Request: Implementing Persistent Speaker Embeddings Across Conversations #227
Hey @juanmc2005, Following to the issue #227, - I have implemented speaker centroids as list of embeddings without mapping, assuming speaker_0 == centroid 0 inside SpeakerDiarization - added a better...
Dear @juanmc2005 Do you know if anyone has managed to get your code to run diarization with transcriptions (https://betterprogramming.pub/color-your-captions-streamlining-live-transcriptions-with-diart-and-openais-whisper-6203350234ef) working on a Raspberry Pi 5? I cannot get diart working...