facebookresearch/encodec issues and pull requests

#84 - Help，Test of pre-trained models

Issue - State: open - Opened by a897456 5 months ago
Labels: question

#83 - Audio Codes "at utterance level"

Issue - State: open - Opened by juanilarregui 5 months ago
Labels: question

#82 - Distributed Section Error in Encodec on Termux

Issue - State: open - Opened by Manamama 6 months ago
Labels: bug

#81 - Preparing Train Dataset (mixing strategy)

Issue - State: open - Opened by kthworks 7 months ago
Labels: question

#80 - High bit rates

Issue - State: open - Opened by vinittech 8 months ago
Labels: question

#79 - RuntimeError Couldn't find appropriate backend to handle uri {uri} and format {format}.

Issue - State: open - Opened by Raviu56 9 months ago - 5 comments
Labels: bug

#78 - fixed lstm autocast

Pull Request - State: open - Opened by calculating 9 months ago - 2 comments
Labels: CLA Signed

#77 - Export Audio

Issue - State: open - Opened by fakerybakery 10 months ago
Labels: question

#76 - Converting encodec model to ONNX

Issue - State: open - Opened by kalradivyanshu 11 months ago
Labels: question

#75 - Fast embedding

Pull Request - State: closed - Opened by turian 11 months ago - 1 comment

#74 - How STFT Discriminator Output Logits are used in Hinge Loss?

Issue - State: open - Opened by steventan0110 11 months ago
Labels: question

#73 - Couldn't reach 'hf-internal-testing/librispeech_asr_dummy' on the Hub

Issue - State: open - Opened by a897456 11 months ago
Labels: question

#72 - Pretrained weights for model without lstm?

Issue - State: open - Opened by muazhuda 12 months ago
Labels: question

#71 - Encoding Long Audio Clips

Issue - State: open - Opened by aviaefrat about 1 year ago - 2 comments
Labels: question

#70 - Streaming example?

Issue - State: open - Opened by bryanhpchiang about 1 year ago - 1 comment
Labels: question

#69 - License of the weights?

Issue - State: open - Opened by muazhuda about 1 year ago
Labels: question

#68 - Interpolation between two audio clips?

Issue - State: open - Opened by jhurliman about 1 year ago - 1 comment
Labels: question

#67 - Balancer for different model outputs

Pull Request - State: open - Opened by gmongaras about 1 year ago - 1 comment
Labels: CLA Signed

#66 - Low quality of the reconstruct audio？

Issue - State: closed - Opened by wotulong about 1 year ago - 2 comments
Labels: question

#65 - training dataset

Issue - State: open - Opened by Tracy-30 about 1 year ago
Labels: question

#64 - RVQ's password book

Issue - State: open - Opened by lizeyu519 about 1 year ago
Labels: question

#63 - MS-STFTDiscriminator: Why concatenation is done in a form of padding the real part?

Issue - State: closed - Opened by ahmed-fau over 1 year ago
Labels: question

#62 - Small Refactoring of the conv.py file

Pull Request - State: open - Opened by GuichardVictor over 1 year ago
Labels: CLA Signed

#61 - Codebook expiration does not take effect at all

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

#60 - Add 🤗 Transformers usage and info

Pull Request - State: closed - Opened by Vaibhavs10 over 1 year ago - 2 comments
Labels: CLA Signed

#59 - Diffusion decoder release

Pull Request - State: closed - Opened by Sparker17 over 1 year ago
Labels: CLA Signed

#57 - RuntimeError: No audio I/O backend is available

Issue - State: open - Opened by vvirtues over 1 year ago - 5 comments
Labels: question

#56 - Changing existing models and training them

Issue - State: open - Opened by NikSuPNU over 1 year ago - 1 comment
Labels: question

#55 - Question about better quality models for 48 kHz

Issue - State: closed - Opened by StephanAXX over 1 year ago - 2 comments
Labels: question

#54 - ConvLayerNorm returns None?

Pull Request - State: open - Opened by ws-choi over 1 year ago - 2 comments

#53 - Could this be used for a better quality audiolm

Issue - State: open - Opened by y-71 over 1 year ago - 3 comments
Labels: question

#52 - Finetuning possible?

Issue - State: open - Opened by turian over 1 year ago - 5 comments
Labels: question

#51 - How to draw the audio thumbnail？

Issue - State: open - Opened by ABC0408 over 1 year ago
Labels: question

#50 - 16kHz model is needed!

Issue - State: open - Opened by lifeiteng over 1 year ago - 3 comments
Labels: question

#49 - Non-free LICENSE

Issue - State: closed - Opened by TechnologyClassroom over 1 year ago - 3 comments

#48 - Commercial-Friendly License Available?

Issue - State: closed - Opened by bitnom over 1 year ago - 1 comment
Labels: question

#47 - How backward balancer when using huggingface accelerate

Issue - State: open - Opened by skiiwoo over 1 year ago
Labels: question

#46 - Motivation behind `layer_state` in `StreamingTransformerEncoder`

Issue - State: open - Opened by mxkrn over 1 year ago - 1 comment
Labels: question

#45 - VQ code vectors

Issue - State: closed - Opened by listener17 over 1 year ago - 6 comments
Labels: question

#44 - the definition of loss_l

Issue - State: open - Opened by wl3b10s over 1 year ago
Labels: question

#43 - how does it work for resampling 16k wav to 24k wav?

Issue - State: open - Opened by MisakaMikoto96 over 1 year ago - 1 comment
Labels: question

#42 - Entropy coding

Issue - State: open - Opened by diff7 over 1 year ago - 2 comments
Labels: question

#41 - Add readme comment clarifying num quantizers

Pull Request - State: closed - Opened by LWprogramming over 1 year ago - 1 comment
Labels: CLA Signed

#40 - fix sample_rate to frame_rate where appropriate

Pull Request - State: closed - Opened by LWprogramming over 1 year ago - 1 comment
Labels: CLA Signed

#39 - Number of codebooks and calculation of bitrates

Issue - State: open - Opened by rkstgr over 1 year ago - 5 comments
Labels: question

#38 - A question about adversarial loss

Issue - State: open - Opened by BakerBunker over 1 year ago - 3 comments
Labels: question

#37 - Question about bitrate choices

Issue - State: open - Opened by VivekPanyam over 1 year ago - 3 comments
Labels: question

#36 - Questions about dataset mixture strategy

Issue - State: closed - Opened by zerlinwang over 1 year ago - 2 comments
Labels: question

#35 - EOFError encounted for some special audio lengths

Issue - State: closed - Opened by chenjiasheng over 1 year ago - 2 comments
Labels: bug

#34 - Wrong device in average_metrics function

Issue - State: open - Opened by AndreyBocharnikov over 1 year ago - 1 comment
Labels: bug

#33 - incorrect time to expire codes

Issue - State: open - Opened by AndreyBocharnikov over 1 year ago - 1 comment
Labels: bug

#32 - Reconstruction Loss

Issue - State: open - Opened by AndreyBocharnikov over 1 year ago - 3 comments
Labels: question

#31 - chore: fix small typo error

Pull Request - State: closed - Opened by 0xflotus over 1 year ago - 1 comment
Labels: CLA Signed

#30 - get_bandwidth_per_quantizer is incorrect.

Issue - State: closed - Opened by bfs18 over 1 year ago - 1 comment
Labels: bug

#29 - fix typo in distrib.py

Pull Request - State: closed - Opened by eltociear over 1 year ago - 1 comment
Labels: CLA Signed

#28 - Wrong bar chart on announcement

Issue - State: open - Opened by signalwerk over 1 year ago - 1 comment
Labels: bug

#27 - Will there be some audio samples of `Model architecture Analysis` part ?

Issue - State: closed - Opened by BakerBunker over 1 year ago - 1 comment
Labels: question

#26 - Can the decoder models run on Android and IOS ?

Issue - State: open - Opened by zdhernandez over 1 year ago - 1 comment
Labels: question

#25 - Zero grad in residual vq

Issue - State: open - Opened by npuichigo almost 2 years ago - 8 comments
Labels: bug

#24 - Channel-mismatch `RuntimeError` when extracting embedding with 24kHz model

Issue - State: closed - Opened by leranjun almost 2 years ago - 4 comments
Labels: bug

#23 - what is the ECDC File?

Issue - State: open - Opened by alihamid996 almost 2 years ago - 1 comment
Labels: question

#22 - Pre-trained Discriminator ??

Issue - State: open - Opened by compressor1212 almost 2 years ago - 1 comment
Labels: question

#21 - Low quality audio in the demo clip

Issue - State: open - Opened by itsTyrion almost 2 years ago - 7 comments
Labels: question

#20 - the value of the residual vector quantization commitment loss

Issue - State: open - Opened by zjj1333 almost 2 years ago - 3 comments
Labels: question

#19 - Memory leak in decoding process

Issue - State: closed - Opened by kevmo314 almost 2 years ago - 2 comments
Labels: bug

#18 - Real-world Balancer usage question

Issue - State: closed - Opened by shenberg almost 2 years ago - 5 comments
Labels: question

#17 - During Training model's loss doesn't converge

Issue - State: closed - Opened by compressor1212 almost 2 years ago - 2 comments
Labels: question

#16 - Some details about RVQ code

Issue - State: open - Opened by yangdongchao almost 2 years ago - 5 comments
Labels: question

#15 - Questions about the pre-trained language model

Issue - State: open - Opened by Xue9901 almost 2 years ago - 4 comments
Labels: question

#14 - How to use to iOS and Android

Issue - State: closed - Opened by wengxianxun almost 2 years ago - 1 comment
Labels: question

#13 - Invalid file: WindowsPath of encodec using Windows OS.

Issue - State: closed - Opened by MartinEesmaa almost 2 years ago - 4 comments
Labels: bug

#12 - Could this be used to compare audio similarity?

Issue - State: open - Opened by youssefabdelm almost 2 years ago - 1 comment
Labels: question

#11 - Using the casual model with 24 kHz results in the process being "Killed"

Issue - State: closed - Opened by Macusercom almost 2 years ago - 3 comments
Labels: bug

#10 - Trying to compress what's the formel

Issue - State: open - Opened by EnCodecwtf almost 2 years ago - 4 comments
Labels: question

#9 - About audio quality evaluation

Issue - State: closed - Opened by sh-lee-prml almost 2 years ago - 5 comments
Labels: question

#8 - Weather today

Issue - State: closed - Opened by ezinne-247 almost 2 years ago

#7 - About the stability of the VQ based approach for codec

Issue - State: open - Opened by syang1993 almost 2 years ago - 1 comment
Labels: question

#5 - Do we have training examples?

Issue - State: open - Opened by ChuxiJ almost 2 years ago - 17 comments
Labels: question

#4 - Inference using a GPU

Issue - State: closed - Opened by lucasbr15 almost 2 years ago - 2 comments
Labels: question

#3 - SoundStream improved reimplementation

Issue - State: open - Opened by kwinz almost 2 years ago - 1 comment
Labels: question

#2 - Minimal code improvements

Pull Request - State: closed - Opened by ghost almost 2 years ago
Labels: CLA Signed

#1 - Real-time usage example, and permissive licensing question

Issue - State: open - Opened by josephrocca almost 2 years ago - 9 comments
Labels: question

GitHub / facebookresearch/encodec issues and pull requests