r9y9/wavenet_vocoder issues and pull requests

#222 - Merged

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

#221 - How to training a WaveNet model with different sample rate?

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

#220 - Cant train

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

#219 - I cant even use Wavenet pre-trained

Issue - State: closed - Opened by kosumosuSpb about 2 years ago - 1 comment

#218 - spectrogram (image) to wav

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

#217 - librosa error on stage 2 of gaussian run.sh ParameterError: Audio data must be floating-point

Issue - State: closed - Opened by Barigamb738 over 2 years ago - 3 comments

#216 - NOT AN ISSUE: Fixed colab notebook to work as of October 14th, 2021

Issue - State: open - Opened by qwertyuu about 3 years ago - 6 comments

#215 - Input Data and Targets while training the Wavenet using MOL

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

#214 - Slow Inference

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

#213 - Autograd-Issue for Training Gaussian WaveNet

Issue - State: open - Opened by lambda-delta34 over 3 years ago

#212 - Can't load data

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

#211 - Train error

Issue - State: closed - Opened by ben-8878 almost 4 years ago

#210 - Speech Marks

Issue - State: closed - Opened by genabotpub almost 4 years ago - 2 comments
Labels: question, wontfix

#209 - Multi-speaker TTS with ESPnet mel-spectrograms

Issue - State: open - Opened by migi-gon almost 4 years ago

#208 - The speed of inference is too slow

Issue - State: closed - Opened by c1a1o1 almost 4 years ago - 1 comment
Labels: wontfix

#207 - batch_wavegen() call issue

Issue - State: open - Opened by Latzy47 about 4 years ago

#206 - Load pretrained model state_dict error ,when run synthesis.py

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

#205 - About Different Size between Predicted-mel and Preprocess-mel

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

#204 - Error when using pretrained model with mel-sepcs from "deepvoice3-pytorch"

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

#203 - why it needs 'train.txt' in evaluate.py when I input the mel files(.npy) ？

Issue - State: closed - Opened by ymzlygw about 4 years ago

#202 - Installation issue

Issue - State: closed - Opened by jun-danieloh over 4 years ago

#201 - Rayhane-mamah Tacotron-2 + r9y9 wavenet_vocoder compatibility

Issue - State: open - Opened by Alexey322 over 4 years ago - 1 comment

#200 - Could someone explain how these dimensions of Wavenet layers work, as they appear to mismatch?

Issue - State: closed - Opened by jjoe1 over 4 years ago - 1 comment
Labels: wontfix

#199 - Low GPU Usage - Cache/DataLoader Issue?

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

#198 - run.sh file is missing(bash: ./run.sh: No such file or directory)

Issue - State: closed - Opened by sweetcode75 over 4 years ago
Labels: wontfix

#196 - Training directory error

Issue - State: closed - Opened by ghost over 4 years ago - 3 comments
Labels: wontfix

#195 - Training Error from train.py files

Issue - State: closed - Opened by nathphoenix over 4 years ago - 1 comment
Labels: wontfix

#194 - Training error

Issue - State: closed - Opened by nathphoenix over 4 years ago
Labels: wontfix

#193 - Training error

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

#192 - preprocess error

Issue - State: closed - Opened by nathphoenix over 4 years ago - 4 comments
Labels: wontfix

#191 - ModuleNotFoundError: No module named 'audio'

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

#190 - preprocess error

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

#189 - tensorflow error in notebook file

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

#188 - Different Audio quality among intermediate results

Issue - State: open - Opened by auspicious3000 over 4 years ago - 2 comments

#187 - When using MOL recipe, run.sh throws ValueError: min() arg is an empty sequence

Issue - State: closed - Opened by m-k-S over 4 years ago - 1 comment

#186 - Running wavenet with low inference

Issue - State: closed - Opened by qo4on over 4 years ago - 1 comment
Labels: wontfix

#185 - Update README.md

Pull Request - State: closed - Opened by JasonGhent over 4 years ago

#184 - Providing new spectrogram to synthesis.wavegen method

Issue - State: closed - Opened by m-k-S over 4 years ago - 2 comments

#183 - Help extending to MAILabs data - Warbly speech - MoL, 1000k steps

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

#182 - Train with Multi-speaker Dataset

Issue - State: open - Opened by r406 over 4 years ago - 1 comment

#181 - _pad_2d bug in the stable version v0.1.1.

Issue - State: open - Opened by lmxyy over 4 years ago
Labels: bug

#180 - Fast wavenet

Issue - State: closed - Opened by narcise almost 5 years ago - 1 comment

#179 - local and global conditioning features for cmu-arctic dataset results

Issue - State: closed - Opened by shiva1393 almost 5 years ago - 6 comments

#178 - Local and global conditioning feature

Issue - State: closed - Opened by shiva1393 almost 5 years ago - 1 comment
Labels: question

#177 - KeyError when trying to parse hparams json file

Issue - State: closed - Opened by Fredrum almost 5 years ago - 4 comments
Labels: bug

#176 - Colab failing for me on wavegen( line!

Issue - State: closed - Opened by Fredrum almost 5 years ago - 1 comment
Labels: bug

#175 - Update README.md

Pull Request - State: closed - Opened by Sadam1195 about 5 years ago - 2 comments

#174 - Input text

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

#173 - cannot import name 'version'

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

#172 - normalization method

Issue - State: closed - Opened by james20141606 about 5 years ago - 1 comment

#171 - Fix lengths in train.py

Pull Request - State: closed - Opened by bajibabu about 5 years ago - 3 comments

#170 - pitch shifted output

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

#169 - how to control upsample scales

Issue - State: open - Opened by james20141606 about 5 years ago - 12 comments
Labels: wontfix

#167 - Which version for training unconditional WaveNet?

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

#166 - Generalization ability?

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

#165 - train.txt in train.py

Issue - State: closed - Opened by james20141606 about 5 years ago - 9 comments

#164 - Refactor a lot: add several new features and misc improvements

Pull Request - State: closed - Opened by r9y9 about 5 years ago

#163 - "quantize_channels" parameter in JSON file

Issue - State: closed - Opened by byuns9334 about 5 years ago - 1 comment
Labels: question

#162 - emotional voice

Issue - State: closed - Opened by tiblop over 5 years ago - 1 comment
Labels: question, wontfix

#161 - Run a demo server

Issue - State: closed - Opened by adjouama over 5 years ago - 1 comment
Labels: wontfix

#160 - README: add list of papers that used the repository

Issue - State: closed - Opened by r9y9 over 5 years ago - 1 comment

#159 - Fixing broken dependencies (lws, bandmat) on macOS 10.14

Issue - State: closed - Opened by TheButlah over 5 years ago - 6 comments
Labels: bug

#158 - about the sampling rate or data rate

Issue - State: closed - Opened by nkcdy over 5 years ago - 2 comments
Labels: question

#157 - Gaussian WaveNet

Issue - State: closed - Opened by r9y9 over 5 years ago - 3 comments
Labels: new feature

#156 - Training issues

Issue - State: closed - Opened by xbsdsongnan over 5 years ago

#153 - About the exact iteration number of LJSpeech pretrained model

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

#151 - How can speed be adjusted of a new if trained on a pre trained model?

Issue - State: closed - Opened by ishansan38 over 5 years ago - 1 comment
Labels: wontfix, insufficient information

#145 - Tacotron-2 synthesis.py cannot synthesize text

Issue - State: closed - Opened by popo0293 over 5 years ago - 1 comment

#141 - WaveNet as a Virtual instrument

Issue - State: closed - Opened by henrycornish almost 6 years ago - 1 comment
Labels: question, wontfix

#140 - Reduce background noise to match Google quality?

Issue - State: closed - Opened by duvtedudug almost 6 years ago - 3 comments
Labels: wontfix, discussion

#138 - Possible to produce good quality unconditional speech?

Issue - State: closed - Opened by realtimecrime almost 6 years ago - 2 comments
Labels: wontfix

#137 - Noisy voice generated when audio dataset have variable amplitude.

Issue - State: closed - Opened by rishikksh20 almost 6 years ago - 2 comments
Labels: wontfix

#135 - Support for generating multiple(>1) audio at one time

Pull Request - State: closed - Opened by mazzzystar almost 6 years ago

#132 - Regarding resuming from checkpoint

Issue - State: closed - Opened by jseplae almost 6 years ago - 3 comments
Labels: wontfix

#127 - mu-law encoded data: ValueError: [(128, -128), (0, 0)] cannot contain negative values.

Issue - State: closed - Opened by jseplae about 6 years ago - 5 comments
Labels: bug

#117 - Tacotron2 TTS demo: Adapt to the latest tensorflow

Issue - State: open - Opened by r9y9 about 6 years ago - 13 comments
Labels: help wanted, Google Colab

#113 - How speed up the Wavenet synthesis？

Issue - State: closed - Opened by peter05010402 about 6 years ago - 12 comments
Labels: wontfix

#111 - why not use greedy decoding?

Issue - State: closed - Opened by wenyong-h about 6 years ago - 7 comments
Labels: wontfix, discussion

#100 - Unsuccessful Input texts to be synthesized

Issue - State: closed - Opened by dsilva-tbox over 6 years ago - 1 comment
Labels: wontfix

#99 - Dimensions in the model do not correspond to dimensions in the size

Issue - State: closed - Opened by dsilva-tbox over 6 years ago - 1 comment
Labels: wontfix

#98 - Thank you for your open source, I noticed that 20180510_mixture_lj_checkpoint_step000320000_ema.json frame_shift_ms=0 in this file, why should I set this up?

Issue - State: closed - Opened by sunnnnnnnny over 6 years ago - 2 comments

#97 - Thank you for your open source, I noticed that 20180510_mixture_lj_checkpoint_step000320000_ema.json frame_shift_ms=0 in this file, why should I set this up?

Issue - State: closed - Opened by sunnnnnnnny over 6 years ago - 2 comments

#92 - Hello, if I want to use your pre-trained wavenet model, what are the specific requirements for the mel spectrogram dimension generated by speech synthesis?

Issue - State: closed - Opened by sunnnnnnnny over 6 years ago - 2 comments

GitHub / r9y9/wavenet_vocoder issues and pull requests