Ecosyste.ms: Issues

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

GitHub / neonbjb/tortoise-tts issues and pull requests

#818 - Model files not found when installing by docker

Issue - State: open - Opened by Hamlet626 18 days ago - 2 comments

#816 - Wrong Windows installations guide in README

Issue - State: open - Opened by arturstopa 23 days ago - 3 comments

#815 - can someone help me this tts work?

Issue - State: open - Opened by Rod6969 27 days ago

#814 - Can this be used to redub videos?

Issue - State: open - Opened by jazir555 about 1 month ago - 1 comment

#812 - Dev opt

Pull Request - State: closed - Opened by supermomo668 about 1 month ago

#811 - Tortoise tts

Issue - State: open - Opened by MrrVii about 1 month ago

#810 - about the speech speaker condition selection

Issue - State: open - Opened by JohnHerry about 2 months ago

#809 - Fixing issues with Docker Setup

Pull Request - State: closed - Opened by nikitalokhmachev-ai about 2 months ago

#808 - urdu language help

Issue - State: open - Opened by paisekamao about 2 months ago - 1 comment

#806 - taking a long time to process text to speech

Issue - State: open - Opened by mdemarco1234 2 months ago

#803 - get no benefit from the CLVP module

Issue - State: open - Opened by JohnHerry 2 months ago - 2 comments

#802 - integration with Ollama

Issue - State: open - Opened by andsty 3 months ago - 2 comments

#801 - need more help about diffusion finetune

Issue - State: closed - Opened by JohnHerry 3 months ago - 2 comments

#797 - live streaming socket

Pull Request - State: closed - Opened by kunci115 3 months ago - 2 comments

#796 - Cannot install via Docker

Issue - State: open - Opened by blackcatstudiosdevelopment 3 months ago - 4 comments

#792 - cant install couldnt find scipy.tar.gz

Issue - State: open - Opened by YousefMohamed101 3 months ago - 7 comments

#790 - female and male voice mixed on

Issue - State: closed - Opened by xalteropsx 3 months ago - 1 comment

#788 - why voice is too much noisy?

Issue - State: open - Opened by zehranrgi 4 months ago

#786 - "yes" bug

Issue - State: open - Opened by cesinsingapore 4 months ago

#785 - Commerical use

Issue - State: closed - Opened by bar9532 4 months ago - 1 comment

#783 - Building Docker for Cuda fails weirdly

Issue - State: open - Opened by blackcatstudiosdevelopment 4 months ago - 1 comment

#782 - Anny

Issue - State: open - Opened by Lion2404 4 months ago

#781 - Inconsistent Voice Timbre in Synthesized Speech

Issue - State: open - Opened by yuan1615 4 months ago - 1 comment

#780 - need some more detailed information about the training data distribution

Issue - State: closed - Opened by JohnHerry 4 months ago - 5 comments

#779 - 💀💀💀 Docker Container will not compile

Issue - State: open - Opened by PeterTucker 4 months ago - 1 comment

#777 - adding a parameter check for device.

Pull Request - State: closed - Opened by damithsenanayake 4 months ago

#776 - TextToSpeech device always automatically selected

Issue - State: open - Opened by damithsenanayake 4 months ago - 1 comment

#775 - Can't build on WSL2 in Docker

Issue - State: open - Opened by PeterTucker 4 months ago

#774 - setup.cfg: fix warning

Pull Request - State: closed - Opened by newAM 4 months ago

#773 - is M1 support a proof of concept for now?

Issue - State: open - Opened by working-name 4 months ago

#772 - Package project with Nix

Pull Request - State: closed - Opened by Yanall-Boutros 5 months ago - 1 comment

#770 - Requesting to add it in Pinokio

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

#769 - English

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

#768 - Reconsider release training script

Issue - State: open - Opened by prassanna-ravishankar 5 months ago

#765 - Fix help information for use_deepspeed flag

Pull Request - State: closed - Opened by olishevskii 5 months ago

#764 - Does the type parameter contain the correct value?

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

#763 - ModuleNotFoundError: No module named 'beartype'

Issue - State: open - Opened by SammBrooks 5 months ago - 2 comments

#762 - Where to find the generated sound sample?

Issue - State: closed - Opened by zhouhao27 5 months ago - 1 comment

#760 - Update Dockerfile to enable CUDA pytorch

Pull Request - State: closed - Opened by Fmstrat 5 months ago

#759 - why cut speech_conditioning_inputs.shape[1] agian?

Issue - State: open - Opened by conver334 5 months ago

#758 - ModuleNotFoundError: No module named 'progressbar'

Issue - State: open - Opened by e4strick 6 months ago

#756 - Problem generating tts with trained model

Issue - State: closed - Opened by krimt1984 6 months ago

#755 - how do i use pregenerated conditioning latents?

Issue - State: open - Opened by lobsterchan27 6 months ago - 3 comments

#754 - about the struct of ConditioningEncoder

Issue - State: open - Opened by donglc20 6 months ago

#752 - read_fast.py script breaks without cuda

Issue - State: open - Opened by vicbois390 6 months ago

#751 - Issue with tokenizers

Issue - State: open - Opened by PatiB87 6 months ago - 2 comments

#750 - Update tts_stream.py

Pull Request - State: open - Opened by GHUFRAN-HYDER 6 months ago - 2 comments

#741 - AttributeError: module 'numpy' has no attribute 'complex'

Issue - State: open - Opened by ashish-yadav-911 7 months ago - 1 comment

#738 - Is additional training possible with tortoise-tts?

Issue - State: open - Opened by kbuwel 7 months ago - 4 comments

#736 - Dockerfile - updated transformers version to 4.31.0

Pull Request - State: closed - Opened by a-zurcher 7 months ago - 2 comments

#735 - DeepSpeed on Windows

Issue - State: open - Opened by molan1976 7 months ago - 1 comment

#734 - preset

Issue - State: open - Opened by molan1976 7 months ago - 1 comment

#732 - Utilities not found

Issue - State: open - Opened by eliich 7 months ago - 3 comments

#728 - Failed building wheel for tokenizers

Issue - State: open - Opened by ks-kasra 7 months ago - 6 comments

#716 - update transformers to v4.36.1 (has a downside)

Pull Request - State: closed - Opened by rsxdalv 8 months ago - 3 comments

#694 - Batch Inference?

Issue - State: open - Opened by addytheyoung 10 months ago - 1 comment

#690 - Update do_tts.py args

Pull Request - State: closed - Opened by Chapoly1305 10 months ago

#675 - If using any voice except "random" it is lead to error

Issue - State: open - Opened by UserOnion 11 months ago - 4 comments

#671 - diffusion gone in api_fast?

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

#668 - Minor updates, preparation for MPS support for fast API

Pull Request - State: closed - Opened by fakerybakery 11 months ago

#656 - Add finetuning to repo

Issue - State: open - Opened by fakerybakery 11 months ago - 1 comment

#650 - Make voice file extension comparison case-insensitive

Pull Request - State: closed - Opened by reterVision 11 months ago

#649 - run tortoise-tts on several gpus at once

Issue - State: open - Opened by MagicChakram 11 months ago - 5 comments

#624 - I can confirm this will run with NO GPU

Issue - State: closed - Opened by wgaylord 12 months ago - 2 comments

#622 - libaio .so error on win 11

Issue - State: open - Opened by gavinv587BC 12 months ago - 4 comments

#604 - preset and use_deepspeed have the same help in do_tts.py

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

#588 - do_tty.py gives CUFF error

Issue - State: open - Opened by iplayfast about 1 year ago - 2 comments

#574 - Absolute fastest inference speed

Issue - State: open - Opened by SinanAkkoyun about 1 year ago - 15 comments

#567 - How to customize for another language

Issue - State: open - Opened by rohanjhanepal about 1 year ago - 12 comments

#550 - Added MPS support

Pull Request - State: closed - Opened by Jerry-Master about 1 year ago - 27 comments

#545 - The sampling algorithm is ddpm or ddim?

Issue - State: closed - Opened by ruaruaruabick about 1 year ago - 4 comments

#539 - CUDA out of memory

Issue - State: open - Opened by gjin10969 about 1 year ago - 6 comments

#517 - Beginner questions about Tortoise TTS and cloning from audio clips

Issue - State: open - Opened by jackpotcityco about 1 year ago - 7 comments

#493 - Cantonese + English model

Issue - State: closed - Opened by Keith-Hon about 1 year ago - 4 comments

#486 - ModuleNotFoundError: No module named 'tortoise'

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

#450 - Error: Wheel "progressbar'

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

#416 - Stop Audio cut off at the end/is there a way to add time buffer?

Issue - State: open - Opened by jtfl28 over 1 year ago - 6 comments

#399 - Memory leak progressively running out of ram

Issue - State: open - Opened by SarahPeterson2854 over 1 year ago - 7 comments

#393 - ModuleNotFoundError: No module named 'einops'

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

#375 - Training "Thorsten-Voice" german TTS model

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

#369 - Unable to create new voice profile.

Issue - State: open - Opened by OutcastsAnonymous over 1 year ago - 9 comments

#305 - python setup.py bdist_wheel did not run successfully.

Issue - State: open - Opened by vipankumar87 over 1 year ago - 6 comments

#298 - libtorchaudio.pyd not found when trying to use tortoise.

Issue - State: open - Opened by MancV21 over 1 year ago - 7 comments

#280 - is there any way to make it read longer like 20-30mins?

Issue - State: closed - Opened by philsouth over 1 year ago - 39 comments

#226 - Can this be trained in spanish?

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

#196 - ModuleNotFoundError: No module named 'tortoise.models'

Issue - State: closed - Opened by Fluffpumpkin almost 2 years ago - 8 comments

#192 - Errors when running preset

Issue - State: closed - Opened by elvisish almost 2 years ago - 6 comments

#164 - Non english model

Issue - State: open - Opened by iRanadheer almost 2 years ago - 11 comments

#37 - GPU Out of Memory

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

#9 - The resulting voice doesn't sound much like me

Issue - State: closed - Opened by Randy-H0 over 2 years ago - 7 comments