haoheliu/AudioLDM2

Issues

• 输入的文本可以作为歌词么？

  #80 opened 3 months ago by ucas010
  2

• AudioLDM2 via Pinokio -- CUDA out of memory...

  #43 opened a year ago by Ai-ways
  2

• Suggestion: Assert that pytorch compiled with CUDA support *before* the 30+ minute load.

  #85 opened a month ago by jacksonlevine
  0

• Evaluation Protocol

  #76 opened 5 months ago by MoayedHajiAli
  1

• Segmentation Fault when providing transcript

  #83 opened 2 months ago by AvivNavon
  0

• Individual style transfer for text to speech

  #82 opened 2 months ago by Tortoise17
  0

• Customizing voice / tone generation with specific input vocal

  #60 opened 2 months ago by Tortoise17
  0

• Style transfer text_to_speech

  #62 opened 2 months ago by Tortoise17
  0

• Example of using super_resolution_and_inpainting with diffusers?

  #81 opened 2 months ago by tin2tin
  0

• Audioldm2-full checkpoints for finetune?

  #79 opened 4 months ago by Tortoise17
  0

• cannot import name 'VitsModel' from 'transformers'

  #75 opened 5 months ago by XinleiNIU
  2

• is their a way to change speaker

  #77 opened 5 months ago by xalteropsx
  0

• AudioMAE on huggingface

  #61 opened a year ago by fundwotsai2001
  1

• Will the image-to-audio model be open?

  #32 opened a year ago by Hangsiin
  2

• Plans to release AudioLDM2 training code?

  #71 opened 9 months ago by MoayedHajiAli
  1

• What data is used for training the different checkpoints?

  #73 opened 8 months ago by fibr1900
  0

• Hello, i use Seait and i have a problem

  #69 opened 9 months ago by AlexIves16
  1

• What is the config of model "audioldm_48k"

  #68 opened 9 months ago by ivcy0928
  0

• Can't "import gradio as gr" but I've installed gradio

  #67 opened 10 months ago by LuZixuan2022
  0

• AttributeError: module 'gradio' has no attribute 'Box'

  #52 opened a year ago by dm701
  5

• where should models be put in?

  #26 opened a year ago by xiaohong23
  2

• 48k checkpoint not working

  #64 opened 10 months ago by jmlemercier
  0

• pretrained_model in class FirstStagePostProcessor(nn.Module)?

  #63 opened 10 months ago by yeori1
  0

• Web app just keeps processing forever and not doing anything at all.

  #55 opened a year ago by Newbie82659
  1

• Is there a version that runs on CPU?

  #27 opened a year ago by Njasa2k
  1

• .

  #59 opened a year ago by Tortoise17
  1

• Examples don't work

  #58 opened a year ago by SoftologyPro
  0

• Model dropdown does not work

  #57 opened a year ago by SoftologyPro
  0

• Is there any docs on how to run the Text to Speech?

  #29 opened a year ago by DamienDeepgram
  5

• Can't load tokenizer for 'roberta-base'.

  #47 opened a year ago by hello-xiaow
  2

• Training code

  #49 opened a year ago by BestVicky
  2

• License

  #56 opened a year ago by fakerybakery
  1

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

  #54 opened a year ago by bigpon
  0

• How can I train this model by myself ?

  #53 opened a year ago by Nyuo70
  0

• Question about AudioMAE details

  #50 opened a year ago by jacklishufan
  0

• Strange sampling before the gradio demo starts

  #48 opened a year ago by 4eJIoBek1
  0

• LocalEntryNotFoundError

  #46 opened a year ago by BestVicky
  0

• Function to go from raw audio to LOA

  #41 opened a year ago by miraodasilva
  1

• Optimisation 3: Torch Compile in blog fails

  #45 opened a year ago by tiansiyuan
  0

• Collection of audio generated with audioldm2

  #44 opened a year ago by timtensor
  0

• Reproducing results on AudioCaps

  #42 opened a year ago by chevalierNoir
  0

• Could you provide the ChatGPT prompt of sound?

  #25 opened a year ago by LinB203
  5

• Cuda out of memory?

  #40 opened a year ago by Betterzhou1997
  2

• Cannot import name 'AudioLDM2Pipeline' from 'diffusers

  #34 opened a year ago by AB00k
  2

• Windows not yet supported for torch.compile

  #39 opened a year ago by uviachen
  0

• Text to Speech for AudioLDM 2 pipeline on Huggingface?

  #37 opened a year ago by filip-michalsky
  0

• Doc string Update?

  #36 opened a year ago by rajveer43
  0

• gradio运行报错

  #33 opened a year ago by luyao-cv
  0

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

  #30 opened a year ago by carlosalvidrez
  2

• Installation and running error on M2 Mac

  #28 opened a year ago by hoominchu
  2