Ecosyste.ms: Issues

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

GitHub / jaywalnut310/vits issues and pull requests

#223 - ETAs for training?

Issue - State: open - Opened by IngwiePhoenix 2 months ago

#222 - 显存占用很高

Issue - State: open - Opened by Gooddz1 3 months ago

#221 - Runtime error

Issue - State: open - Opened by SameerSri72 5 months ago - 1 comment

#220 - License Question

Issue - State: open - Opened by UmerrAhsan 5 months ago

#219 - 是否可以通过java去实现训练和推理？

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

#216 - intersperse function explain

Issue - State: open - Opened by chnk58hoang 6 months ago

#214 - Flip module explain

Issue - State: closed - Opened by chnk58hoang 8 months ago - 1 comment

#213 - Code doesn;t even run. so many errors intalling pip

Issue - State: open - Opened by thenaivekid 8 months ago - 6 comments

#211 - Continue training VITS

Issue - State: closed - Opened by Pipe1213 9 months ago - 2 comments

#210 - No audio generated

Issue - State: open - Opened by zhouhao27 9 months ago

#209 - Can't install requirement

Issue - State: closed - Opened by zhouhao27 9 months ago - 1 comment

#208 - Multi node Support

Issue - State: open - Opened by Ahmed-Hossam-Aldeen 10 months ago

#206 - VITS model Conversion to ONNX and TFLite.

Issue - State: open - Opened by tusharhchauhan 10 months ago - 2 comments

#204 - Option for Single GPU?

Issue - State: open - Opened by hoomexsun 11 months ago - 2 comments

#203 - [CONTRIBUTION] Speech Dataset Generator

Issue - State: open - Opened by davidmartinrius 11 months ago

#202 - NCCL error windows

Issue - State: open - Opened by Vubni about 1 year ago - 1 comment

#201 - How is the Out of Dictionary texts created?

Issue - State: closed - Opened by deep-convai about 1 year ago

#200 - Problems adding a new speaker

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

#199 - having numpy complex error

Issue - State: open - Opened by M-Usamah about 1 year ago - 1 comment

#198 - [Question] about improve quality audio

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

#196 - Negative loss_dur

Issue - State: open - Opened by staceystaceystacey about 1 year ago - 1 comment

#195 - Fine-tune with multiple speakers' data.

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

#194 - DistributedBucketSampler : create bucket sampler issue.

Issue - State: open - Opened by YoungJae98 about 1 year ago - 1 comment

#193 - How to use trained model in inference?

Issue - State: open - Opened by solee0022 over 1 year ago - 2 comments

#192 - How to locate the spreak time of each word

Issue - State: open - Opened by huwenkai26 over 1 year ago

#191 - Transfer learning and fine-tuning tts

Issue - State: open - Opened by ToiYeuTien over 1 year ago - 3 comments

#190 - Is there a way to do batch inference?

Issue - State: open - Opened by SoulflareRC over 1 year ago - 3 comments

#189 - Some of the losses increasing during training?

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

#188 - How to continue training from the previous stopped epoch?

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

#187 - VITS codes failed to run for Python 3.10.12

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

#186 - progress keeps resetting, checkpoint fails to load properly

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

#184 - Training time too long

Issue - State: open - Opened by newton2149 over 1 year ago

#181 - segmentation fault after train a few steps

Issue - State: open - Opened by zhufeijuanjuan over 1 year ago - 6 comments

#180 - running vits on Ventura GPU

Issue - State: closed - Opened by dnabanita7 over 1 year ago - 1 comment

#179 - Can I also train an Italian model?

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

#178 - Is there some way to force a break?

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

#177 - Iserting new symbols in a pre-trained model

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

#176 - Issue with training at 8000Hz

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

#175 - Duration Issue with the generated audio

Issue - State: open - Opened by Aliasgarsaifee over 1 year ago - 3 comments

#174 - ModuleNotFoundError: No module named 'unidecode'

Issue - State: open - Opened by amrzv over 1 year ago - 3 comments

#173 - Explanation for loss_disc, loss_gen, loss_fm,loss_mel, loss_kl?

Issue - State: open - Opened by chigkim over 1 year ago - 3 comments

#172 - How can I know the number of steps?

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

#171 - Cloning voices

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

#170 - How to use ground truth durations to train vits?

Issue - State: closed - Opened by 16dian11 over 1 year ago - 5 comments

#169 - VITS2?

Issue - State: open - Opened by OnceJune over 1 year ago - 4 comments

#168 - Question about the TextEncoder

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

#167 - Why using z but not flow(z_p, spk_emb) for decoder ?

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

#166 - Korean Multi-speaker Model Convergence Failure

Issue - State: closed - Opened by heesuju over 1 year ago - 4 comments

#164 - negative loss

Issue - State: open - Opened by JunhaoHuang0615 over 1 year ago

#162 - Runtime error

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

#160 - Training a 8k Model as LJSpeech.

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

#159 - Computing power requirement

Issue - State: open - Opened by JoyceMind over 1 year ago - 3 comments

#158 - Training is too slow. WHY?

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

#156 - Problem with export model to onnx

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

#155 - About KL Divergence loss

Issue - State: open - Opened by ylzz1997 over 1 year ago - 1 comment

#153 - GPU multiprocess error

Issue - State: open - Opened by deryaguler95 over 1 year ago - 1 comment

#152 - How to train a multilingual model

Issue - State: open - Opened by liuxiong21 over 1 year ago - 2 comments

#149 - python build_ext don't automatically create dir

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

#146 - ValueError: too many values to unpack (expected 2)

Issue - State: open - Opened by wrl1224 over 1 year ago - 3 comments

#142 - mac m1 inference

Issue - State: open - Opened by zdj97 almost 2 years ago - 2 comments

#135 - IndexError: Dimension out of range (expected to be in range of [-1, 0], but got 1)

Issue - State: closed - Opened by Arszr almost 2 years ago - 15 comments

#134 - Training for custom dataset

Issue - State: open - Opened by huydang2106 almost 2 years ago - 4 comments

#132 - Silence when generating audio

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

#131 - 在训练的时候我遇到了一些问题

Issue - State: open - Opened by C9H20sx almost 2 years ago - 4 comments

#123 - Multis-speaker identity degradation

Issue - State: open - Opened by NikitaKononov about 2 years ago - 4 comments

#122 - Is it normal to wait a long time between each epoch？

Issue - State: open - Opened by HuaHuaOfficial about 2 years ago - 4 comments

#121 - Inference result is not as good as the demo

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

#106 - Problems about training with multiprocess

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

#104 - what is difference between val.text and train.txt

Pull Request - State: open - Opened by queechy about 2 years ago

#100 - Fix typo in modules.py

Pull Request - State: open - Opened by eltociear about 2 years ago

#99 - What is the relative position method

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

#98 - vits is awsome! Can vits train with emotional dataset?

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

#97 - 你好，想拿来试试运行在colab，但是不成功

Pull Request - State: closed - Opened by upright2003 about 2 years ago - 2 comments

#94 - 没人反馈这个语音API目前失效了吗

Issue - State: open - Opened by xingyunlee12138 over 2 years ago

#93 - 没人反馈这个语音API目前失效了吗....

Pull Request - State: closed - Opened by xingyunlee12138 over 2 years ago - 1 comment

#92 - Questions about the Korean datasets

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

#91 - Question about strange voice

Issue - State: open - Opened by panxin801 over 2 years ago

#90 - Error on tensor size & How to config with 16KHz waves?

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

#89 - Is there any method which can adjust the speed of synthesized speech?

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

#88 - size mismatch for enc_p.emb.weight

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

#87 - How many steps should we train to get the best results?

Issue - State: open - Opened by futureaiengineeer over 2 years ago - 12 comments

#86 - I want to train VITS model for URDU language

Issue - State: open - Opened by Muhammad-Afnan-Akram over 2 years ago

#85 - Mispronounce some words and 44,1 Khz audio

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

#84 - Can I use it without GPU?

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