Ecosyste.ms: Issues

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

GitHub / maum-ai/voicefilter issues and pull requests

#35 - Bump torch from 1.0.1 to 2.2.0

Pull Request - State: open - Opened by dependabot[bot] 4 months ago
Labels: dependencies

#34 - commit for colab

Pull Request - State: closed - Opened by 3unsh0t 9 months ago

#32 - how to work for multi noise

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

#30 - Cannot reproduce reported SDR & retrain the speaker embedding

Issue - State: open - Opened by nnbtam99 almost 3 years ago

#29 - Question about wav2spec function in utils/audo.py

Issue - State: open - Opened by HieDean about 3 years ago

#28 - question about ffmpeg-normalize

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

#27 - Adding specific versions to librosa and numba

Pull Request - State: closed - Opened by johannesmols about 4 years ago - 3 comments

#26 - Is the VoiceFilter model checkpoint available to be used directly?

Issue - State: open - Opened by salonijain18 over 4 years ago - 1 comment

#25 - Training setting problem

Issue - State: open - Opened by Morank88 over 4 years ago - 6 comments

#23 - inference

Issue - State: closed - Opened by kurbobo over 4 years ago

#22 - the model implementation comprehension

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

#21 - hop_length and win_length

Issue - State: closed - Opened by ksellesk almost 5 years ago

#20 - Can you get the initial mean SDR on LibriSpeech using Google's test list?

Issue - State: open - Opened by weedwind about 5 years ago - 8 comments

#19 - embedder.pt with new dataset

Issue - State: closed - Opened by Devid29 about 5 years ago - 4 comments

#18 - [WIP] implement power low compression loss

Pull Request - State: open - Opened by stegben about 5 years ago - 8 comments

#17 - install Pillow for PIL

Pull Request - State: closed - Opened by stegben about 5 years ago - 2 comments

#16 - search for flac instead of wav when normalize

Pull Request - State: closed - Opened by stegben about 5 years ago

#15 - fix pytorch version to 1.0.1

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

#14 - Need to try power-law compression loss

Issue - State: open - Opened by seungwonpark about 5 years ago - 2 comments

#13 - Question about utils/evaluation.py

Issue - State: open - Opened by lawlict about 5 years ago - 2 comments

#12 - Question when training VoiceFilter

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

#11 - Question when preprocessing wav files

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

#10 - Question about normalize-resample.sh

Issue - State: closed - Opened by yxixi over 5 years ago - 4 comments

#9 - Question about start point of SDR

Issue - State: closed - Opened by lycox1 over 5 years ago - 4 comments

#8 - how to create file embedder

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

#7 - fianl model

Issue - State: closed - Opened by 0ifeng0 over 5 years ago - 7 comments

#6 - use torch.no_grad scope when inferencing

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

#5 - VoiceFilter realization problem

Issue - State: closed - Opened by va-volokhov over 5 years ago - 8 comments

#4 - Out of memory when Inferencing a single file.

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

#3 - Real-time inference

Issue - State: closed - Opened by kyungjin-lee over 5 years ago - 4 comments

#2 - The files from the dataset are in flac format

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

#1 - Try partial convolution padding scheme

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