haoheliu / AudioLDM

AudioLDM: Generate speech, sound effects, music and beyond, with text.

https://audioldm.github.io/

haoheliu/AudioLDM Issues

WebUI not functioning
Closed 2 months ago1
Infinite audio generation
Updated 2 months ago6
Question about the code during the text embedding calculation
Updated 3 months ago
Output singing as well as instruments ?
Updated 4 months ago2
AttributeError: module 'gradio' has no attribute 'Box'
Updated 5 months ago1
Status or info on Mac silicon GPU support ?
Updated 6 months ago2
Hope to release the training code
Closed 6 months ago2
fine-turning
Closed a year ago1
NameError: name '_C' is not defined
Closed 6 months ago2
Error: Unexpected key(s) in state_dict: "cond_stage_model.model.text_branch.embeddings.position_ids".
Closed 6 months ago3
Training
Closed 7 months ago
The vae decoder cannot recover original audio with the extracted latent code
Updated 7 months ago2
Change outputs permission
Updated 7 months ago3
audio-to-audio: is it possible to use more than one samples?
Updated 7 months ago
How to contribute?
Updated 7 months ago
Error: RuntimeError: Error(s) in loading state_dict for LatentDiffusion:
Closed 7 months ago1
ONNX support
Updated 7 months ago1
I am having this issue
Updated 7 months ago3
cuda
Updated 8 months ago
RuntimeError: Expected weight to be a vector of size equal to the number of channels in input, but got weight of shape [128] and input of shape [128, 256, 16]
Updated 8 months ago2
Is there any docs on how to run Super Resolution?
Closed 9 months ago2
Is there any docs on how to run the Text to Speech?
Closed 9 months ago2
add torch.device("mps") to devices for apple M1 suppport
Updated 9 months ago2
Unexpected key(s) error
Updated 10 months ago2
RuntimeError: Error(s) in loading state_dict for LatentDiffusion: Unexpected key(s) in state_dict: "cond_stage_model.model.text_branch.embeddings.position_ids".
Updated 10 months ago6
Output generated via command line tool not saved if prompt is very long
Updated 10 months ago
Text-guided Audio-to-Audio Style Transfer
Updated 10 months ago
init_audio_file error
Updated 10 months ago3
Multi-GPU support?
Updated 10 months ago
Are there plans to train a 44.1kHz stereo model?
Updated 10 months ago2
Request for separate pretrained HiFiGAN and Autoencoder checkpoints
Updated 10 months ago4
Error:class_labels should be provided when num_class_embeds > 0
Updated 10 months ago
CondaValueError: invalid package specification: python=3.8;
Updated 10 months ago1
CLAP checkpoint
Updated 10 months ago3
RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory
Updated 10 months ago4
How to configure for Mac silicon Intel and AMD
Updated a year ago4
'ffmpeg' is not recognized error in Web APP
Updated a year ago1
Colab notebook broken
Updated a year ago2
Duration must be a multiple of 2.5 second
Updated a year ago
how to control the duration of the generated samples
Updated a year ago
Pretrained CLAP in different checkpoints
Updated a year ago
Negative prompts
Updated a year ago
Request for finetuned models on huggingface space
Updated a year ago2
Request: Enable device "cpu" support for experimental purposes
Updated a year ago1
audioldm-m-text-ft ckpt to huggingface model
Updated a year ago1
AssertionError: Torch not compiled with CUDA enabled
Closed a year ago
How to generate 1 second or less audio ?
Closed a year ago
CUDA out of memory with default setup [Windows]
Updated a year ago1
Could you provide the training script and the training sequence of several models in it?
Updated a year ago
清问能否提供训练脚本，还有里面的几个模型的训练顺序是怎么样的？
Updated a year ago