Ecosyste.ms: Issues

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

GitHub / facebookresearch/denoiser issues and pull requests

#162 - Output with distortion

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

#160 - how to use local model ?

Issue - State: open - Opened by chinarui-na over 1 year ago

#159 - Seeking Clarification on DemucsStreamer Logic

Issue - State: open - Opened by sreezilosky over 1 year ago - 1 comment

#158 - Can not remove noise at the first seconds

Issue - State: open - Opened by ILG2021 over 1 year ago

#157 - Commercial use?

Issue - State: open - Opened by grazder over 1 year ago - 2 comments

#155 - Denoiser doesn't works properly

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

#154 - Data DNS load is bug

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

#153 - Fine-tuning with custom data

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

#152 - access to pretrained weight

Issue - State: open - Opened by woojung-son over 1 year ago - 1 comment

#151 - Using denoiser at all doesn't work at all

Issue - State: open - Opened by GUUser91 almost 2 years ago - 1 comment

#150 - Question about the implemented of SpectralConvergengeLoss

Issue - State: open - Opened by mcw519 almost 2 years ago

#149 - How do I use the pre-train model?

Issue - State: closed - Opened by GUUser91 almost 2 years ago

#148 - Wasm model conversion

Issue - State: open - Opened by zeynepgulhanuslu almost 2 years ago

#147 - Update README.md

Pull Request - State: open - Opened by jhkonan almost 2 years ago - 1 comment

#146 - where are the models?

Issue - State: open - Opened by dewijones92 almost 2 years ago

#145 - My valid loss =0, is this normal?

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

#144 - Causal model results on Valentini

Issue - State: open - Opened by VenkateshParvathala almost 2 years ago

#143 - Very distorted output

Issue - State: open - Opened by MohammedMehdiTBER almost 2 years ago

#142 - Help please

Issue - State: open - Opened by Sinicyn78 almost 2 years ago

#141 - Reduce noise cancellation degree

Issue - State: closed - Opened by dgoryeo about 2 years ago - 4 comments

#140 - Multi-channel Audio Enhancement

Issue - State: open - Opened by TankyFranky about 2 years ago - 1 comment

#139 - fix: init `conv_state` and `lstm_state` when calling `flush` method

Pull Request - State: closed - Opened by hoyaaaa about 2 years ago - 3 comments
Labels: CLA Signed

#137 - Suggestion for flush method of DemucsStreamer

Issue - State: closed - Opened by hoyaaaa about 2 years ago

#136 - Enhancement Request: Browser plugin

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

#135 - CUDA out of memory

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

#134 - Pretrained model

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

#133 - need pretrained model for 8KHz speech

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

#132 - Processing bytes instead of numpy array (Using PyAudio)

Issue - State: open - Opened by qalabeabbas49 over 2 years ago - 1 comment

#131 - Using RTP packet stream as input and output!!

Issue - State: open - Opened by qalabeabbas49 over 2 years ago

#130 - Is 'sample' and 'frame' has same meaning?

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

#129 - How Can I use this code in real time?

Issue - State: open - Opened by rltgjqmthf over 2 years ago

#128 - Can I use that code on real-time?(by CoLAB)

Issue - State: closed - Opened by PLEASEHELPMEPEOPLE over 2 years ago - 1 comment

#127 - Want to use that code in CoLAB

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

#126 - Very long training time for DNS 2020

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

#125 - I can not reproduce the result that reported in the paper

Issue - State: open - Opened by KhanhNguyen4999 over 2 years ago - 8 comments

#124 - What are the minimum system requirements ?

Issue - State: open - Opened by the-drunk-coder over 2 years ago - 2 comments

#123 - Segmentation fault on macos 12.3.1

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

#122 - Question: file input and output?

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

#120 - suggested dataset size for custom model?

Issue - State: open - Opened by markhanslip almost 3 years ago - 2 comments

#119 - Is there any non-stationary noise in interspeech2020/master?

Issue - State: open - Opened by st3inum almost 3 years ago - 3 comments

#118 - No documented setup works

Issue - State: closed - Opened by jhkonan almost 3 years ago - 6 comments

#117 - The enhance doesn't generate denoised file

Issue - State: closed - Opened by peace20162 almost 3 years ago - 7 comments

#116 - How to achieve audio split frame and window in the code?

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

#115 - demucs v3

Issue - State: open - Opened by isgursoy almost 3 years ago - 1 comment

#114 - Problem about using denoiser as preprocess

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

#113 - AttributeError: 'HydraConfig' object has no attribute 'hydra'

Issue - State: open - Opened by TonTonTWMAN almost 3 years ago - 5 comments

#111 - Deepstream/GStreamer Pipeline

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

#109 - Mistake in the documentation of the dry parameter

Issue - State: closed - Opened by Nithin-Holla almost 3 years ago - 2 comments

#108 - Online Normalization details question

Issue - State: open - Opened by abugler almost 3 years ago - 1 comment

#107 - SOUNDFLOWER-2CH can't able to execute in mac

Issue - State: closed - Opened by BlackSpy1231 about 3 years ago - 1 comment

#106 - RuntimeError: cuDNN error: CUDNN_STATUS_EXECUTION_FAILED

Issue - State: closed - Opened by takashin3391 about 3 years ago - 3 comments

#105 - missing one positional arg 'sr'

Issue - State: closed - Opened by shipleyxie about 3 years ago - 3 comments

#104 - How to improve the speed of streaming implementation？

Issue - State: closed - Opened by lingdhox about 3 years ago - 3 comments

#103 - Convert to ONNX

Issue - State: closed - Opened by anjul1008 about 3 years ago - 2 comments

#102 - Reference and Output (signal) tensor size mismatch when computing STOI.

Issue - State: closed - Opened by sangeet2020 about 3 years ago - 2 comments

#101 - denoiser.enhance doesnt generate denoied file

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

#100 - Deploy it in Android

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

#99 - Bus error (core dumped) when run in jupyterhub docker

Issue - State: open - Opened by szhaoyu about 3 years ago - 1 comment

#98 - denoiser.live can't connect to sink interface

Issue - State: closed - Opened by codeuntilcold about 3 years ago - 4 comments

#97 - DNS evaluation metric

Issue - State: closed - Opened by IdoWSC about 3 years ago - 2 comments

#96 - Enhance pre-recorded audio files from script

Issue - State: closed - Opened by jianupetrut about 3 years ago - 2 comments

#95 - Problem running LIVE speech enhancement on Linux

Issue - State: open - Opened by hadaso about 3 years ago - 1 comment

#94 - Reproduce Results with DNS synthesize configuration

Issue - State: closed - Opened by IdoWSC about 3 years ago - 3 comments

#93 - Mac using BlackHole 2ch instead of SoundFlower

Issue - State: open - Opened by imomin over 3 years ago - 8 comments

#92 - How to modify parameters for training other samples with high sampling rate?

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

#91 - Use output of lstm as embeddings for classification task

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

#90 - Facing error while using pretrained model

Issue - State: open - Opened by amiyamandal-dev over 3 years ago - 6 comments

#89 - Multiprocessing error with large number of files

Issue - State: open - Opened by HarisNaveed17 over 3 years ago - 5 comments

#88 - 8k data situation and a question for training

Issue - State: open - Opened by chw18019 over 3 years ago - 1 comment

#87 - CUDA out of memory when set --device="cuda"

Issue - State: closed - Opened by Lethanhson9901 over 3 years ago - 2 comments

#86 - where do I download pretrained models?

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

#85 - Theoretical and technical details

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

#84 - overkilled

Issue - State: open - Opened by yfliao over 3 years ago - 6 comments

#83 - denoiser.enhance hanged and crashed in the end

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

#82 - Value of Frame Size

Issue - State: open - Opened by diams4iot-blockchain over 3 years ago - 1 comment

#81 - Couple of suggestions

Issue - State: closed - Opened by stolpa4 over 3 years ago - 2 comments

#80 - tradeoffs to think about when training this model on 48khz data?

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

#79 - Bug when training with DDP

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

#78 - ALSA lib pcm.c:8306:(snd_pcm_recover) underrun occurred

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

#77 - A pre-trained model trained only on valentini dataset

Issue - State: open - Opened by VenkateshParvathala over 3 years ago - 5 comments

#76 - Questions about model

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

#75 - Fix work without test data

Pull Request - State: closed - Opened by kventinel over 3 years ago
Labels: CLA Signed

#74 - Down sampling questions

Issue - State: open - Opened by winddori2002 over 3 years ago - 3 comments

#73 - High RTF with cuda device in streaming mode

Issue - State: open - Opened by SolomidHero almost 4 years ago - 1 comment

#72 - PESQ is smaller than paper

Issue - State: open - Opened by LexiYIN almost 4 years ago - 3 comments

#71 - Questions on reproducing results with DNS 48kHz

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

#70 - Loss variance between validation and test

Issue - State: open - Opened by winddori2002 almost 4 years ago - 2 comments

#69 - Input resampling buffer is always the same in the streamer (Bug)

Issue - State: closed - Opened by stolpa4 almost 4 years ago - 1 comment

#68 - TypeError: cannot unpack non-iterable AudioMetaData object

Issue - State: closed - Opened by 0xd3ba almost 4 years ago - 3 comments

#67 - Bad performance in real time.

Issue - State: open - Opened by sagyHarpaz almost 4 years ago - 5 comments

#66 - fixing recent torchaudio support

Pull Request - State: closed - Opened by adefossez almost 4 years ago - 1 comment
Labels: CLA Signed

#65 - pip install defaults to torch version 1.8

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

#64 - How to enhance pre-recorded audios?

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

#63 - Got 'RuntimeError: CUDA out of memory'

Issue - State: closed - Opened by ntyoshi almost 4 years ago - 6 comments