github.com/mozilla/TTS issues | Ecosyste.ms: OpenCollective

How to prevent this weird sounding output?

gnusupport opened this issue 15 days ago

porblem execute :pip install -e .

kamal26071973 opened this issue 2 months ago

Versus Mozilla Ocho LlamaFile Whisper

bphd opened this issue 3 months ago

Illegal Instruction (core dumped) Fedora 35

lvto2000 opened this issue 4 months ago

how do you synthesize speech with already trained model?

Izolovi4 opened this issue 4 months ago

Hello, can you make an app for android?

Glazami opened this issue 4 months ago

unable to generate anything

gucio321 opened this issue 5 months ago

TTS seems incompatible with python 3.12

rmmonster opened this issue 6 months ago

Processing text leads to looped speech output

hartmutobendorf opened this issue 7 months ago

any directml support?

neonarc4 opened this issue 11 months ago

Failed to build numpy

ralyodio opened this issue about 1 year ago

The path where the model saved in windows 11 is different from what it was showing in the terminal

kabildeveloper opened this issue about 1 year ago

TypeError: BaseDatasetConfig.init() got an unexpected keyword argument 'name'

iaclaudioia8 opened this issue about 1 year ago

Columns and DataType Not Explicitly Set on line 196 of prepare_voxceleb.py

CodeSmileBot opened this issue about 1 year ago

Update README.md

DantSu opened this pull request about 1 year ago

bring bark back

robertsw22 opened this issue about 1 year ago

AttributeError: module 'TTS.tts.datasets' has no attribute ''

DasKeksSchwert3 opened this issue over 1 year ago

我想訓練人工智慧機械人的声音, 模仿我的声音, 請問 Mozilla TTS 能幫到我嗎？

tonkabean630 opened this issue over 1 year ago

Numpy Version Incompatability

hankp46 opened this issue over 1 year ago

Cannot install on Macbook Pro M1 max

curiousbee2020 opened this issue over 1 year ago

Instructions in Readme produce buzzing sound

TheNotary opened this issue over 1 year ago

ModuleNotFoundError: No module named 'TTS.tts.datasets.preprocess'

dawit3228 opened this issue over 1 year ago

Okay since this package is clearly inactive please archive this repository or else I will report your organization to Github's Code Safety Team

ZipingL opened this issue over 1 year ago

I believe that I most make a point of privileged revival and state that my computer is giving me this odd error as well. Mozilla team? I guess now that it has[ been nine years since I have last used](https://gist.github.com/ZipingL/bd8c19d798acc99918a30c434f3c78d5) @Mozilla-GitHub-Standards related Common Voice, Deep Voice programs, there really has not been any changes...

ZipingL opened this issue over 1 year ago

I don't know how to measure dataset quality, asking for help

dawenxi-only opened this issue over 1 year ago

speaker_encoder module is missing the train.py file

ontheway-arch opened this issue over 1 year ago

Now i'm using tflite model for iOS. Can anyone help me?

HuongPlc opened this issue almost 2 years ago

Run tts error: 'utf-8' codec can't decode byte 0x80

hejinlong opened this issue almost 2 years ago

Fix: Typo multiband

OrIOg opened this pull request almost 2 years ago

error in --list_speaker_idxs

ghost opened this issue about 2 years ago

Error in conversion from Torch to TF model

nfaraji2002 opened this issue about 2 years ago

Website

Cutedimpledboy opened this issue about 2 years ago

short word with server no finish

greatAznur opened this issue about 2 years ago

version 0.6.1

shad94 opened this pull request over 2 years ago

how to run tts after I installed tts through 'pip install tts'

ZpWaitingForSunshine opened this issue over 2 years ago

Trainer stops working without error messages

rezareza007 opened this issue over 2 years ago

hangup. server crash

GabrieleRisso opened this issue over 2 years ago

Installation in python venv fails armx64

dawiinci opened this issue over 2 years ago

Missing `f` prefix on f-strings fix

code-review-doctor opened this pull request over 2 years ago

Missing `f` prefix on f-strings

code-review-doctor opened this issue over 2 years ago

THIS REPO IS NOT MAINTAINED - PLS USE https://github.com/coqui-ai/TTS

d3on4pcsm opened this pull request almost 3 years ago

THIS REPO IS NOT MAINTAINED -- USE https://github.com/coqui-ai/TTS

d3on4pcsm opened this issue almost 3 years ago

Garbage Collection issue

MultiTrickFox opened this issue almost 3 years ago

Archive unmaintained TTS repo

JRMeyer opened this issue almost 3 years ago

Resource temporarily unavailable

bphd opened this issue almost 3 years ago

The boy Model

Richtechwy opened this issue almost 3 years ago

RuntimeError: failed to find espeak library

Jzow opened this issue almost 3 years ago

How can we don't save test_audios in any directory? where is the config related to saving test_audios?

arminsoltan opened this issue almost 3 years ago

Reformat Directory Structure

QazCetelic opened this pull request almost 3 years ago

Tacotron (2?) based models appear to be limited to rather short input

deliciouslytyped opened this issue about 3 years ago

Readme shows how to get program, but not which models correspond to advertisement at top

deliciouslytyped opened this issue about 3 years ago

synthesize more than one audio simultaneously on the same GPU ?

fabianoluzbr opened this issue about 3 years ago

AttributeError: 'AttrDict' object has no attribute 'gst'

camoverride opened this issue about 3 years ago

Windows 10 RuntimeError: failed to load espeak library [WinError 193] during training

bondi7 opened this issue about 3 years ago

> Decoder stopped with `max_decoder_steps` 500

Osiris-Team opened this issue about 3 years ago

ModuleNotFoundError: TTS.tts.datasets.preprocess

luis-vera opened this issue about 3 years ago

Timeout when I try to start training

luis-vera opened this issue about 3 years ago

TTS synthesis via pip module throws torch exception for short phrases

mischief opened this issue about 3 years ago

Avoid robotisation on Multi Speaker TTS

TheMrZZ opened this issue about 3 years ago

Wrong pronunciation of short forms words like 'USA', 'UN' , 'MSN'

Nimesh1993 opened this issue over 3 years ago

Fixed installation instructions for fresh Ubuntu 18

stefan-reich opened this issue over 3 years ago

WINDOWS: returns FALSE, when I test my cuda through the "test_cude.py" file that was instructed to create (the SOF post to how to download this library onto windows), Plus, a question about the GPU requirements of this library.

adam-TAU opened this issue over 3 years ago

Why has this not been ported to MacOS? Could you please add this capability ASAP because I would like to use TTS in my repository very soon?

shyamalschandra opened this issue over 3 years ago

ValueError: not enough values to unpack (expected 4, got 1)

wanghaisheng opened this issue over 3 years ago

SyntaxError: Non-ASCII character '\xc3' in file setup.py

Dardan1410 opened this issue over 3 years ago

Evlaution Stats are going up while the Training Stats decreasing

HeminQadir opened this issue over 3 years ago

Fix comment mistake

ElJaviLuki opened this pull request over 3 years ago

configure initial and final silence in the synthesized audio file

fabianoluzbr opened this issue over 3 years ago

ruslan tacotron2-DDC download link is broken

egorgam opened this issue over 3 years ago

Centos7 Error during MozillaTTS installation

luis-vera opened this issue over 3 years ago

ERROR: Command errored out with exit status 1: OSError: [WinError 193] %1 is not a valid Win32 application

ishandutta2007 opened this issue over 3 years ago

Emotional text to speech

luantunez opened this issue over 3 years ago

RuntimeError: size mismatch for embedding.weight

luis-vera opened this issue over 3 years ago

Can it be trained for Bengali language

nafeesmahbub opened this issue over 3 years ago

Empty .wav files

Wayne-wonderai opened this issue over 3 years ago

Can't run on Windows

hohuynhminhhieu opened this issue over 3 years ago

'numpy/arrayobject.h' file not found

XiangNanLi opened this issue over 3 years ago

add --in_path for input files

emilonpt opened this pull request over 3 years ago

Add simple usage example

99991 opened this pull request over 3 years ago

Demo server link on https://github.com/mozilla/TTS/wiki/FAQ is broken

curiousbee2020 opened this issue over 3 years ago

support chinese language

yuzhoufengg2 opened this issue over 3 years ago

utils/io.py cannot load config.json due to encoding error (and 1 more)

UnforeseenOcean opened this issue over 3 years ago

RuntimeError: CUDA error: unspecified launch failure

luis-vera opened this issue over 3 years ago

ZeroDivisionError on empty text

wyattscarpenter opened this issue over 3 years ago

Input from file

wyattscarpenter opened this issue over 3 years ago

UnicodeDecodeError: 'charmap' codec can't decode byte 0x81 in position 3230: character maps to <undefined>

creativejaved opened this issue over 3 years ago

Wavegrad training on Arabic data set Bug report.

Amels404 opened this issue over 3 years ago

about hinge loss

hdmjdp opened this issue over 3 years ago

fix(docs): corrects typo in project README

plan-do-break-fix opened this pull request over 3 years ago

Tacotron2 decoder input size when using speaker embedding and GST embedding

nicemanis opened this issue over 3 years ago

[SpeedySpeech] VAL AVG LOSS: NaN

ductho9799 opened this issue over 3 years ago

Pip install TTS does not work python39.2

krperry opened this issue over 3 years ago

Add training script for MB-MelGAN on LjSpeech

chiragoel opened this pull request over 3 years ago

Fix: text is longer than the threshold

bthiban opened this pull request almost 4 years ago

`bidirectional_decoder` appears broken in dev

GuyPaddock opened this issue almost 4 years ago

OSError: sndfile library not found

GuyPaddock opened this issue almost 4 years ago

If validation set contains multiple files, ground truth is length of longest

GuyPaddock opened this issue almost 4 years ago

How Can I build my own vocoder model

luis-vera opened this issue almost 4 years ago

Resuming transfer learning causes previous learning to be lost

GuyPaddock opened this issue almost 4 years ago

WaveRNN missing scale_stats.npy

Pr0Pennypacker opened this issue almost 4 years ago