Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / juanmc2005/diart issues and pull requests

#251 - added method for a save wavform as wav format

Pull Request - State: open - Opened by m15kh 6 days ago

#250 - Returning real time waveform

Issue - State: open - Opened by m15kh 11 days ago - 5 comments
Labels: duplicate

#249 - extracting unique speaker embeddings from pipeline

Issue - State: open - Opened by Aduomas 17 days ago

#248 - Maintaining state across file audio source chunks

Issue - State: open - Opened by Aduomas 17 days ago

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

Issue - State: open - Opened by nikifori 21 days ago - 1 comment
Labels: question

#246 - save a segment of that model is predicted

Issue - State: open - Opened by m15kh 21 days ago - 2 comments
Labels: question

#245 - streamig voice activity detection with own model

Issue - State: closed - Opened by m15kh 24 days ago - 1 comment
Labels: question

#144 - Speaker-blind speech recognition

Pull Request - State: open - Opened by juanmc2005 over 1 year ago - 3 comments
Labels: bug, feature, API, refactoring

#117 - Where the output will be saved after using diart.stream microphone OR when will it stop recording ?

Issue - State: closed - Opened by ankurdhuriya almost 2 years ago - 2 comments
Labels: question

#100 - Fix bug: RTTM output not being patched when closing plot window

Pull Request - State: closed - Opened by juanmc2005 about 2 years ago
Labels: bug

#99 - Unable to select a different microphone

Issue - State: closed - Opened by Shoawen0213 about 2 years ago - 11 comments
Labels: bug

#98 - Paper at JOSS

Issue - State: closed - Opened by juanmc2005 about 2 years ago - 13 comments

#97 - Rolling buffer size / duration in fine-tune segmentation model

Issue - State: closed - Opened by Shoawen0213 about 2 years ago - 2 comments
Labels: question

#96 - `diart.tune` doesn't initialize to custom hyper-parameters

Issue - State: closed - Opened by juanmc2005 about 2 years ago
Labels: bug

#95 - Add speaker enrollment to `OnlineSpeakerDiarization`

Issue - State: open - Opened by juanmc2005 about 2 years ago
Labels: feature, help wanted

#94 - Add test suite

Issue - State: closed - Opened by juanmc2005 about 2 years ago - 1 comment
Labels: ops

#93 - Simplify installation

Issue - State: closed - Opened by juanmc2005 about 2 years ago - 4 comments
Labels: ops

#92 - Online speaker diarization as a block

Pull Request - State: closed - Opened by juanmc2005 about 2 years ago
Labels: feature, API, refactoring

#91 - Compatibility with torchaudio streams

Pull Request - State: closed - Opened by juanmc2005 about 2 years ago
Labels: feature, API

#90 - Question about Optuna on own pipeline with segmentation model

Issue - State: closed - Opened by Shoawen0213 about 2 years ago - 6 comments
Labels: documentation, question

#89 - Hot fixes

Pull Request - State: closed - Opened by juanmc2005 about 2 years ago
Labels: bug

#88 - Several hot fixes

Pull Request - State: closed - Opened by juanmc2005 about 2 years ago
Labels: bug

#87 - Version 0.5

Pull Request - State: closed - Opened by juanmc2005 about 2 years ago
Labels: bug, documentation, feature, API

#86 - Export csv report in `diart.benchmark` when output is provided

Pull Request - State: closed - Opened by juanmc2005 about 2 years ago
Labels: feature

#85 - Multithreading in `diart.benchmark`

Issue - State: closed - Opened by juanmc2005 about 2 years ago - 5 comments
Labels: feature

#84 - Move `PrecalculatedFeaturesAudioSource` inside `OnlineSpeakerDiarization`

Issue - State: closed - Opened by juanmc2005 about 2 years ago - 1 comment
Labels: feature, API

#83 - Free pipeline from ReactiveX

Issue - State: closed - Opened by juanmc2005 about 2 years ago - 1 comment
Labels: help wanted, API, refactoring

#82 - Question about Optuna

Issue - State: closed - Opened by Shoawen0213 about 2 years ago - 2 comments
Labels: question

#81 - Fix bug with empty RTTMs

Pull Request - State: closed - Opened by zaouk over 2 years ago
Labels: bug

#80 - Bug: Error while patching annotation coming from an empty RTTM

Issue - State: closed - Opened by zaouk over 2 years ago - 1 comment
Labels: bug

#79 - Add model arguments to `diart.stream`, `diart.benchmark` and `diart.tune`

Issue - State: closed - Opened by juanmc2005 over 2 years ago - 1 comment
Labels: API

#78 - Update WebSocketAudioSource

Pull Request - State: closed - Opened by ckliao-nccu over 2 years ago
Labels: bug

#77 - Add websocket compatibility + other improvements

Pull Request - State: closed - Opened by juanmc2005 over 2 years ago - 2 comments
Labels: feature

#76 - Change speed of streaming display to match audio speed

Issue - State: open - Opened by AMITKESARI2000 over 2 years ago - 4 comments
Labels: bug, feature

#75 - Create a documentation page

Issue - State: closed - Opened by juanmc2005 over 2 years ago - 5 comments
Labels: documentation, help wanted

#74 - add `study_or_path` as a Path for conversion from string

Pull Request - State: closed - Opened by AMITKESARI2000 over 2 years ago
Labels: bug, documentation

#73 - Add support for websockets

Issue - State: closed - Opened by juanmc2005 over 2 years ago - 1 comment
Labels: feature, help wanted

#72 - Add support for TCP/UDP

Issue - State: closed - Opened by juanmc2005 over 2 years ago - 1 comment
Labels: feature, wontfix

#71 - Convert out/dir to type Path

Pull Request - State: closed - Opened by AMITKESARI2000 over 2 years ago - 2 comments
Labels: bug

#70 - Feature Request: Export result to csv file

Issue - State: closed - Opened by AMITKESARI2000 over 2 years ago - 2 comments
Labels: feature, help wanted, good first issue, question

#69 - Colab example run

Pull Request - State: open - Opened by AMITKESARI2000 over 2 years ago - 1 comment
Labels: documentation, help wanted, good first issue

#68 - Is it possible to pass raw byte data into the pipeline?

Issue - State: closed - Opened by chanleii over 2 years ago - 16 comments
Labels: duplicate, feature, question

#67 - Integrating with mobile apps

Issue - State: closed - Opened by RahmaYasser over 2 years ago - 2 comments
Labels: feature, question

#66 - Version 0.4

Pull Request - State: closed - Opened by juanmc2005 over 2 years ago
Labels: documentation, feature, API, refactoring

#65 - Add hyper-parameter tuning with optuna

Pull Request - State: closed - Opened by juanmc2005 over 2 years ago
Labels: feature, API, refactoring

#64 - Minor features and improvements

Pull Request - State: closed - Opened by juanmc2005 over 2 years ago
Labels: feature, API, refactoring

#63 - Add tensor typing

Issue - State: open - Opened by juanmc2005 over 2 years ago
Labels: documentation, feature, help wanted, refactoring

#62 - Add mini-tutorial for plugging custom segmentation/embedding models

Issue - State: closed - Opened by juanmc2005 over 2 years ago - 1 comment
Labels: documentation, help wanted, good first issue

#61 - Make `pyannote.audio` optional (still mandatory to run default pipeline)

Pull Request - State: closed - Opened by juanmc2005 over 2 years ago
Labels: documentation, feature, API

#60 - Optionally relax incremental clustering constraints

Issue - State: open - Opened by juanmc2005 over 2 years ago - 2 comments
Labels: feature, help wanted

#59 - Replace `resolve_features` with `TemporalFeatureFormatter`

Pull Request - State: closed - Opened by juanmc2005 over 2 years ago
Labels: refactoring

#58 - Question about changing model in system and real-time issue

Issue - State: closed - Opened by Shoawen0213 over 2 years ago - 11 comments
Labels: question

#57 - Improve pipeline profiling

Issue - State: closed - Opened by juanmc2005 over 2 years ago - 3 comments
Labels: help wanted, API, refactoring

#56 - Version 0.3.0

Pull Request - State: closed - Opened by juanmc2005 over 2 years ago - 1 comment
Labels: bug, documentation, feature, API

#55 - Add `RealTimeInference` and `Benchmark`

Pull Request - State: closed - Opened by juanmc2005 over 2 years ago
Labels: bug, feature, API

#54 - Add python API for `diart.stream` and `diart.benchmark`

Issue - State: closed - Opened by juanmc2005 over 2 years ago - 1 comment
Labels: API

#53 - Add hyper-parameter tuning with optuna

Issue - State: closed - Opened by juanmc2005 over 2 years ago - 1 comment
Labels: feature, help wanted

#52 - Question about produce the system

Issue - State: closed - Opened by Shoawen0213 over 2 years ago - 1 comment
Labels: question

#51 - Add `OverlapAwareSpeakerEmbedding`

Pull Request - State: closed - Opened by juanmc2005 over 2 years ago
Labels: documentation, feature, API

#50 - Question about load model

Issue - State: closed - Opened by Shoawen0213 over 2 years ago - 1 comment
Labels: question

#49 - Add padding to last chunk instead of ignoring it

Issue - State: closed - Opened by juanmc2005 over 2 years ago - 1 comment
Labels: feature, help wanted, good first issue

#48 - Transform `resolve_features()` into `ChunkFeatures` and `TemporalFeatures` classes

Issue - State: closed - Opened by juanmc2005 over 2 years ago - 1 comment
Labels: help wanted, good first issue, refactoring

#47 - Improve some names

Pull Request - State: closed - Opened by juanmc2005 over 2 years ago
Labels: API

#46 - Benchmark script + improvements and bug fixes

Pull Request - State: closed - Opened by juanmc2005 over 2 years ago
Labels: bug, feature

#45 - Add `OverlapAwareSpeakerEmbedding` block

Issue - State: closed - Opened by juanmc2005 over 2 years ago - 1 comment
Labels: feature

#44 - Refactor `OnlineSpeakerClustering`

Issue - State: closed - Opened by juanmc2005 over 2 years ago
Labels: wontfix, refactoring

#43 - Make model blocks compatible with any frame-wise or chunk-wise model

Issue - State: closed - Opened by juanmc2005 over 2 years ago - 1 comment
Labels: feature

#42 - Improve names

Issue - State: closed - Opened by juanmc2005 over 2 years ago - 1 comment
Labels: API

#41 - Rebrand demo script

Issue - State: closed - Opened by juanmc2005 over 2 years ago - 1 comment
Labels: API

#40 - how to use it offline?

Issue - State: closed - Opened by Obile19 over 2 years ago - 1 comment
Labels: duplicate, question

#39 - Benchmarking operator

Issue - State: closed - Opened by juanmc2005 over 2 years ago - 1 comment
Labels: feature

#38 - doc: add citation

Pull Request - State: closed - Opened by hbredin over 2 years ago
Labels: documentation

#37 - How to add ASR

Issue - State: closed - Opened by bitnom over 2 years ago - 2 comments
Labels: question

#36 - Question about reproduce the result

Issue - State: closed - Opened by Shoawen0213 over 2 years ago - 8 comments
Labels: question

#35 - Add batched mode for faster inference on pre-recorded conversations

Issue - State: closed - Opened by juanmc2005 over 2 years ago - 1 comment
Labels: feature

#34 - SpeechBrain embedding compatibility

Issue - State: closed - Opened by nefastosaturo over 2 years ago - 11 comments
Labels: feature, question

#33 - Question about Dataset and Training

Issue - State: closed - Opened by Shoawen0213 over 2 years ago - 2 comments
Labels: question

#32 - Question about Table 1

Issue - State: closed - Opened by Shoawen0213 over 2 years ago - 4 comments
Labels: question

#31 - Adds documentation for some of the classes and methods

Pull Request - State: closed - Opened by zaouk over 2 years ago
Labels: documentation

#30 - Gradio/Streamlit demo on Huggingface Space

Issue - State: open - Opened by hbredin over 2 years ago - 2 comments
Labels: feature

#29 - Python 3.7 compatibility and Port Audio Error

Pull Request - State: closed - Opened by Yagna24 over 2 years ago
Labels: feature

#28 - PortAudio Windows Error and Compatibility on Python3.7

Issue - State: closed - Opened by Yagna24 over 2 years ago - 9 comments
Labels: feature

#27 - Add compatibility with `torchaudio` streams

Issue - State: closed - Opened by juanmc2005 almost 3 years ago - 1 comment
Labels: feature

#26 - How to fetch audio segments in real time from diarization pipeline

Issue - State: closed - Opened by Yagna24 almost 3 years ago - 4 comments
Labels: question

#25 - Version 0.2.1

Pull Request - State: closed - Opened by juanmc2005 almost 3 years ago
Labels: bug

#24 - Fix empty segment in `buffer_output` causing a crash

Pull Request - State: closed - Opened by juanmc2005 almost 3 years ago
Labels: bug

#23 - When I pass Audio File I get this error any ideas?

Issue - State: closed - Opened by CreativeSelf0 almost 3 years ago - 12 comments
Labels: bug

#22 - Version 0.2

Pull Request - State: closed - Opened by juanmc2005 almost 3 years ago
Labels: bug, documentation, feature

#21 - Improve README

Pull Request - State: closed - Opened by juanmc2005 almost 3 years ago - 1 comment
Labels: documentation

#20 - Modular `OutputBuilder` + better demo performance

Pull Request - State: closed - Opened by juanmc2005 almost 3 years ago
Labels: documentation, feature

#19 - Asynchronous microphone reading

Pull Request - State: closed - Opened by juanmc2005 almost 3 years ago
Labels: bug, documentation, feature

#18 - Add Hamming-weighted average to `DelayedAggregation`

Pull Request - State: closed - Opened by juanmc2005 almost 3 years ago
Labels: bug, feature

#17 - RTTM ends too soon when latency > 500ms

Issue - State: closed - Opened by juanmc2005 almost 3 years ago
Labels: bug

#16 - Replace `operators.aggregate()` with `functional.DelayedAggregation`

Pull Request - State: closed - Opened by juanmc2005 almost 3 years ago
Labels: bug, documentation, feature

#15 - My output is different from expected_outputs

Issue - State: closed - Opened by sablea almost 3 years ago - 9 comments
Labels: bug

#14 - Any plan to release the model and training code?

Issue - State: closed - Opened by kli017 almost 3 years ago - 4 comments
Labels: question

#13 - Add Hamming-weighted average option to output aggregation

Issue - State: closed - Opened by juanmc2005 almost 3 years ago
Labels: feature

#12 - Move aggregation to functional module

Issue - State: closed - Opened by juanmc2005 almost 3 years ago
Labels: feature

#11 - Questions about the frequent segmentation

Issue - State: closed - Opened by ORainn almost 3 years ago - 2 comments
Labels: question

#10 - Crash on `MicrophoneAudioSource.read()`

Issue - State: closed - Opened by KannebTo about 3 years ago - 6 comments
Labels: bug