Ecosyste.ms: Issues

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

GitHub / resemble-ai/Resemblyzer issues and pull requests

#95 - Add PEP-561 py.typed file to support type checking

Pull Request - State: open - Opened by p7g 4 months ago

#94 - Fix unsafe `torch.load` by adding `weights_only=True`

Pull Request - State: open - Opened by FlyingFathead 4 months ago

#93 - RuntimeError: Numpy is not available

Issue - State: open - Opened by heartgold512 6 months ago - 1 comment

#92 - How can i train Resemblyzer for Hindi Language?

Issue - State: open - Opened by AdvaitDongre 6 months ago

#91 - Languages of the training data.

Issue - State: open - Opened by caixxiong 6 months ago

#90 - Demo2 not showing any result

Issue - State: open - Opened by dmestudent 11 months ago - 4 comments

#89 - is this speaker embedding better than X-vector?

Issue - State: open - Opened by DaehanKim about 1 year ago

#87 - Update audio.py to fix numpy Deprecation

Pull Request - State: closed - Opened by ajatau over 1 year ago

#86 - What license does resemblyzer fall under?

Issue - State: closed - Opened by ugotsoul over 1 year ago - 1 comment

#85 - AttributeError: module 'numpy' has no attribute 'bool'.

Issue - State: closed - Opened by fseasy over 1 year ago

#84 - Using VoiceEncoder as loss with time domain models

Issue - State: open - Opened by vb000 over 1 year ago

#83 - Speech Diarization

Issue - State: closed - Opened by rajpavan4679 over 1 year ago

#82 - Removed aliases of builtin types like np.int (deprecated)

Pull Request - State: closed - Opened by MattyB95 over 1 year ago - 1 comment

#81 - Getting different speaker embeddings from same wav file on different machine

Issue - State: closed - Opened by predawnang over 1 year ago - 2 comments

#80 - Error while using Resemblyzer

Issue - State: closed - Opened by Waseem-786 almost 2 years ago - 2 comments

#79 - New release plans to include latest changes?

Issue - State: closed - Opened by alexteua almost 2 years ago - 5 comments

#78 - MATPLOTLIB FIGURES NOT DISPLAYING..How to solve this please help..

Issue - State: open - Opened by MrinmoyBoruah about 2 years ago - 2 comments

#77 - How to get time stamps for every speaker change?

Issue - State: open - Opened by nehat005 about 2 years ago

#76 - About pre-trained model

Issue - State: open - Opened by ZhaZhaFon over 2 years ago - 2 comments

#75 - Diarization Graph Issue

Issue - State: open - Opened by sankalpbhatia20 over 2 years ago - 1 comment

#73 - Speaker Verification

Issue - State: open - Opened by dlowe24 over 2 years ago - 2 comments

#72 - The Ability of Speaker Diarization with More Than 2 Speakers

Issue - State: open - Opened by ConnieZi over 2 years ago - 3 comments

#71 - Change some positional librosa args to keyword args

Pull Request - State: closed - Opened by mstopa over 2 years ago

#70 - After diarization, The timestamps I got are irrelevants from original file

Issue - State: open - Opened by teoh79 almost 3 years ago - 3 comments

#69 - Async and parallel processing

Issue - State: open - Opened by frankiedrake almost 3 years ago

#68 - End-to-end trainable model HERE

Issue - State: closed - Opened by JuanFMontesinos about 3 years ago

#67 - Fully trainable pytorch model

Pull Request - State: closed - Opened by JuanFMontesinos about 3 years ago - 2 comments

#66 - Install issue

Issue - State: closed - Opened by Mremenar over 3 years ago - 1 comment

#65 - Cambi

Issue - State: closed - Opened by Josseca over 3 years ago

#64 - Lanzamientos

Issue - State: closed - Opened by Josseca over 3 years ago

#63 - trim out problem in diarization

Issue - State: open - Opened by HedgehogTW over 3 years ago - 1 comment

#62 - Long recordings with an unknown number of speakers

Issue - State: open - Opened by NormanTUD over 3 years ago - 2 comments

#61 - voice_encoder.py samples_per_frame

Issue - State: open - Opened by hbo-lambda over 3 years ago

#60 - diarized speech trimmed from the end

Issue - State: open - Opened by abdou-chabira over 3 years ago

#59 - Mac M1 - Demo utils workaround

Issue - State: open - Opened by Ryojikn over 3 years ago

#58 - Diarization issue

Issue - State: open - Opened by Manu21Iq almost 4 years ago - 2 comments

#57 - dvector 256 contain a lot of 0

Issue - State: closed - Opened by G874713346 almost 4 years ago

#56 - How to get embeddings of audio data streaming from microphone.

Issue - State: open - Opened by gaushh almost 4 years ago - 4 comments

#55 - About Pre-trained Model

Issue - State: open - Opened by chankl3579 almost 4 years ago

#53 - Update demo_utils.py

Pull Request - State: closed - Opened by abhinavms almost 4 years ago - 4 comments

#51 - Resemblyzer is evenly distributed i.e speaker 0 and then speaker 1 and so on..

Issue - State: closed - Opened by sourav1122 almost 4 years ago - 1 comment

#49 - lots of values of d-vector are zero

Issue - State: closed - Opened by liuzhaoo almost 4 years ago - 1 comment

#48 - EER of pre-trained model?

Issue - State: closed - Opened by felixkreuk almost 4 years ago - 2 comments

#47 - demo02 has lot of noise, and Animation is delayed further than 200ms!

Issue - State: open - Opened by zhwtz12345 about 4 years ago - 3 comments

#46 - Fake Voice Detection

Issue - State: open - Opened by CO18325 about 4 years ago

#45 - trimmed at the end

Issue - State: open - Opened by RawadMelhem about 4 years ago - 3 comments

#44 - questions about fetures supported by Resemblyzer

Issue - State: open - Opened by shubhamshukla7 about 4 years ago - 1 comment

#43 - Cannot import "sampling_rate"

Issue - State: closed - Opened by b-zhang93 about 4 years ago - 1 comment

#42 - Cosine similarity is inconsistent with the cluster

Issue - State: closed - Opened by tranctan about 4 years ago - 1 comment

#41 - Re-train on my language domain

Issue - State: open - Opened by v-nhandt21 about 4 years ago - 16 comments

#40 - Clarification on embeddings training

Issue - State: open - Opened by davodesign84 over 4 years ago - 4 comments

#39 - ImportError: cannot import name 'sampling_rate'

Issue - State: closed - Opened by i-bond over 4 years ago - 2 comments

#38 - decode back?

Issue - State: closed - Opened by nestyme over 4 years ago - 1 comment

#37 - demo04 issue

Issue - State: open - Opened by liszhang over 4 years ago - 2 comments

#36 - typo in demo2

Issue - State: closed - Opened by liszhang over 4 years ago - 2 comments

#35 - Custom "weights_fpath" load enhancement

Pull Request - State: closed - Opened by yesseyev over 4 years ago - 5 comments

#34 - demo02_diarization problem

Issue - State: closed - Opened by liszhang over 4 years ago - 3 comments

#32 - What dataset was used to train the model?

Issue - State: closed - Opened by janvainer over 4 years ago - 1 comment

#31 - No figure and no sound when I run demo 02.

Issue - State: closed - Opened by hkhk366 over 4 years ago - 2 comments

#30 - Installation Failed

Issue - State: closed - Opened by vinnitu over 4 years ago - 1 comment

#29 - d-Vectors for UIS-RNN

Issue - State: open - Opened by arthavmane over 4 years ago - 4 comments

#28 - Simple Examples

Issue - State: open - Opened by rubberbird over 4 years ago

#27 - Error opening 'audio_data/test.mp3' : file containers data in an unknown format

Issue - State: closed - Opened by rubberbird almost 5 years ago - 2 comments

#25 - torch.jit.frontend.UnsupportedNodeError: DictComp aren't supported

Issue - State: open - Opened by marcoippolito almost 5 years ago - 1 comment

#24 - Syntax highlighting for example code

Pull Request - State: closed - Opened by breuerfelix almost 5 years ago

#23 - Embeddings from different sources of audio are different

Issue - State: open - Opened by Rahul-Sindhu about 5 years ago

#22 - Disable randomness in demos?

Issue - State: open - Opened by hagenw about 5 years ago - 1 comment

#21 - Fix inclusion of README in setup.py

Pull Request - State: closed - Opened by hagenw about 5 years ago - 1 comment

#20 - Add missing tqdm to requirements_demos.txt

Pull Request - State: closed - Opened by hagenw about 5 years ago - 1 comment

#19 - Getting different clusters for the same speaker

Issue - State: closed - Opened by Rahul-Sindhu about 5 years ago - 1 comment

#18 - train new languages for better detection

Issue - State: closed - Opened by rebotnix about 5 years ago - 2 comments

#17 - Finding out the gender

Issue - State: closed - Opened by Rahul-Sindhu about 5 years ago - 2 comments

#16 - Pre-trained model accuracy

Issue - State: closed - Opened by bharat-patidar about 5 years ago - 1 comment

#15 - Embedding is mostly zero

Issue - State: closed - Opened by dodobyte about 5 years ago - 1 comment

#14 - Hign GPU memory requirement

Issue - State: closed - Opened by rohithkodali about 5 years ago - 6 comments

#13 - Demo 01: Similarity

Issue - State: closed - Opened by sberryman over 5 years ago - 56 comments

#12 - Are demos meant to be non-deterministic?

Issue - State: closed - Opened by nmstoker over 5 years ago - 2 comments

#11 - Mp3 file is not accepted in demo02_diarization.py

Issue - State: closed - Opened by rajacsp over 5 years ago - 6 comments

#10 - Compute embeddings from stream & unsupervised diarization

Issue - State: closed - Opened by shashankpr over 5 years ago - 12 comments

#9 - Model path and hparams

Issue - State: closed - Opened by sberryman over 5 years ago - 14 comments

#8 - More information on dataset and training pipeline

Issue - State: closed - Opened by vanIvan over 5 years ago - 2 comments

#6 - In executing the demos: cannot import name 'UMAP' from 'umap'

Issue - State: closed - Opened by marcoippolito over 5 years ago - 3 comments

#4 - Problems with sndfile

Issue - State: closed - Opened by marcoippolito over 5 years ago - 1 comment

#3 - How many speakers is the modeled trained on?

Issue - State: closed - Opened by auspicious3000 over 5 years ago - 1 comment

#2 - Update short example with numpy import

Pull Request - State: closed - Opened by ZohaibAhmed over 5 years ago - 1 comment

#1 - Package is now pypi-compliant

Pull Request - State: closed - Opened by CorentinJ over 5 years ago