haoheliu/AudioLDM2 issues and pull requests

#84 - fix wired in README.md

Pull Request - State: open - Opened by twobob 5 days ago

#83 - Segmentation Fault when providing transcript

Issue - State: open - Opened by AvivNavon 9 days ago

#82 - Individual style transfer for text to speech

Issue - State: open - Opened by Tortoise17 12 days ago

#81 - Example of using super_resolution_and_inpainting with diffusers?

Issue - State: open - Opened by tin2tin 19 days ago

#80 - 输入的文本可以作为歌词么？

Issue - State: open - Opened by ucas010 about 1 month ago

#79 - Audioldm2-full checkpoints for finetune?

Issue - State: open - Opened by Tortoise17 3 months ago

#78 - superresolution inpainting

Pull Request - State: closed - Opened by Leofltt 3 months ago - 1 comment

#77 - is their a way to change speaker

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

#76 - Evaluation Protocol

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

#75 - cannot import name 'VitsModel' from 'transformers'

Issue - State: closed - Opened by XinleiNIU 4 months ago - 2 comments

#74 - Adding run_cpu.py and run_gpu.py in code

Pull Request - State: open - Opened by wing0529 6 months ago

#73 - What data is used for training the different checkpoints?

Issue - State: open - Opened by fibr1900 6 months ago

#72 - Resolve `'audioldm2' is a package and cannot be directly executed` by adding main.py

Pull Request - State: closed - Opened by lingchuL 6 months ago

#71 - Plans to release AudioLDM2 training code?

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

#70 - Resolved app.py error

Pull Request - State: closed - Opened by wing0529 8 months ago

#69 - Hello, i use Seait and i have a problem

Issue - State: open - Opened by AlexIves16 8 months ago - 1 comment

#68 - What is the config of model "audioldm_48k"

Issue - State: open - Opened by ivcy0928 8 months ago

#67 - Can't "import gradio as gr" but I've installed gradio

Issue - State: open - Opened by LuZixuan2022 8 months ago

#66 - fixed the launch issue by implementing gradio's latest version elements

Pull Request - State: open - Opened by Dhiman-Ajay 8 months ago

#65 - Resolve `AttributeError: module 'gradio' has no attribute 'Box'`

Pull Request - State: closed - Opened by carlthome 9 months ago

#64 - 48k checkpoint not working

Issue - State: closed - Opened by jmlemercier 9 months ago

#63 - pretrained_model in class FirstStagePostProcessor(nn.Module)?

Issue - State: open - Opened by yeori1 9 months ago

#62 - Style transfer text_to_speech

Issue - State: closed - Opened by Tortoise17 9 months ago

#61 - AudioMAE on huggingface

Issue - State: open - Opened by fundwotsai2001 10 months ago - 1 comment

#60 - Customizing voice / tone generation with specific input vocal

Issue - State: closed - Opened by Tortoise17 10 months ago

#59 - .

Issue - State: closed - Opened by Tortoise17 10 months ago - 1 comment

#58 - Examples don't work

Issue - State: open - Opened by SoftologyPro 10 months ago

#57 - Model dropdown does not work

Issue - State: open - Opened by SoftologyPro 10 months ago

#56 - License

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

#55 - Web app just keeps processing forever and not doing anything at all.

Issue - State: open - Opened by Newbie82659 11 months ago - 1 comment

#54 - How to generate speech condition on not only transcripts and descriptions but also audio clip?

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

#53 - How can I train this model by myself ?

Issue - State: open - Opened by Nyuo70 11 months ago

#52 - AttributeError: module 'gradio' has no attribute 'Box'

Issue - State: open - Opened by dm701 11 months ago - 5 comments

#51 - add super resolution and inpainting for audioldm2

Pull Request - State: closed - Opened by a43992899 11 months ago

#50 - Question about AudioMAE details

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

#49 - Training code

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

#49 - Training code

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

#48 - Strange sampling before the gradio demo starts

Issue - State: open - Opened by 4eJIoBek1 11 months ago

#47 - Can't load tokenizer for 'roberta-base'.

Issue - State: closed - Opened by hello-xiaow 11 months ago - 2 comments

#46 - LocalEntryNotFoundError

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

#45 - Optimisation 3: Torch Compile in blog fails

Issue - State: open - Opened by tiansiyuan 12 months ago

#44 - Collection of audio generated with audioldm2

Issue - State: open - Opened by timtensor 12 months ago

#43 - AudioLDM2 via Pinokio -- CUDA out of memory...

Issue - State: open - Opened by Ai-ways 12 months ago - 1 comment

#42 - Reproducing results on AudioCaps

Issue - State: open - Opened by chevalierNoir 12 months ago

#41 - Function to go from raw audio to LOA

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

#40 - Cuda out of memory?

Issue - State: open - Opened by Betterzhou1997 about 1 year ago - 2 comments

#39 - Windows not yet supported for torch.compile

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

#38 - Fix: file name too long to be saved.

Pull Request - State: closed - Opened by Steve235lab about 1 year ago

#37 - Text to Speech for AudioLDM 2 pipeline on Huggingface?

Issue - State: open - Opened by filip-michalsky about 1 year ago

#36 - Doc string Update?

Issue - State: open - Opened by rajveer43 about 1 year ago

#35 - Fixed the typo

Pull Request - State: closed - Opened by shyamsantoki about 1 year ago

#34 - Cannot import name 'AudioLDM2Pipeline' from 'diffusers

Issue - State: closed - Opened by AB00k about 1 year ago - 2 comments

#33 - gradio运行报错

Issue - State: open - Opened by luyao-cv about 1 year ago

#32 - Will the image-to-audio model be open?

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

#31 - [README] Update with diffusers implementation

Pull Request - State: closed - Opened by sanchit-gandhi about 1 year ago

#30 - NotImplementedError: The operator 'aten::upsample_bicubic2d.out' is not currently implemented for the MPS device

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

#29 - Is there any docs on how to run the Text to Speech?

Issue - State: closed - Opened by DamienDeepgram about 1 year ago - 5 comments

#28 - Installation and running error on M2 Mac

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

#27 - Is there a version that runs on CPU?

Issue - State: closed - Opened by ninjasaid2k about 1 year ago - 1 comment

#26 - where should models be put in?

Issue - State: open - Opened by xiaohong23 about 1 year ago - 2 comments

#25 - Could you provide the ChatGPT prompt of sound?

Issue - State: open - Opened by LinB203 about 1 year ago - 5 comments

#24 - In-context learning with TTS model

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

#23 - RuntimeError: Pretrained weights not found for model HTSAT-base.

Issue - State: open - Opened by glory20h about 1 year ago - 3 comments

#22 - How to do Image to Audio?

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

#21 - Whether it's prompt or not affects the results generated？

Issue - State: open - Opened by tanggang1997 about 1 year ago - 1 comment

#20 - RAM issue: MPS backend out of memory

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

#19 - Runtime error: espeak not installed on your system

Issue - State: open - Opened by davidkamp about 1 year ago - 8 comments

#18 - checkpoint for audiomae?

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

#17 - Will there be models for AudioLDM2 that run on 12GB VRAM Cards?

Issue - State: open - Opened by CRCODE22 about 1 year ago - 1 comment

#16 - ERROR: Cannot install transformers 4.32.0.dev0 (from git+https://github.com/huggingface/transformers.git) and transformers==4.30.2 because these package versions have conflicting dependencies.

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

#15 - not working on OSX

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

#14 - New

Issue - State: closed - Opened by RedLegendDev about 1 year ago - 1 comment

#13 - Add support for Apple MPS backend

Pull Request - State: closed - Opened by microboym about 1 year ago - 3 comments

#12 - fix typo in data.py

Pull Request - State: closed - Opened by eltociear about 1 year ago

#11 - Possible Google Colab?

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

#10 - On Windows 11, running audioldm2 gives error "no modules named audioldm2.main"

Issue - State: open - Opened by rfernand2 about 1 year ago - 2 comments

#9 - Steps to create a virtual environment for AudioLDM2?

Issue - State: open - Opened by Gushousekai195 about 1 year ago - 7 comments

#8 - Style Transfer

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

#7 - how to use implement text2speech？

Issue - State: open - Opened by Johnson-yue about 1 year ago - 5 comments

#6 - Unable to run on Mac M1

Issue - State: closed - Opened by glovebx about 1 year ago - 9 comments

#5 - Add API Endpoint "text2audio"

Pull Request - State: closed - Opened by Kamilake about 1 year ago

GitHub / haoheliu/AudioLDM2 issues and pull requests