declare-lab / tango

A family of diffusion models for text-to-audio generation.

https://tango2-web.github.io/

declare-lab/tango Issues

How did you split the MusicCaps dataset into training and testing sets?
Updated 13 days ago
laugh
Closed 2 months ago
Evaluation Protocol
Closed 2 months ago2
Fine-Tuning TANGO 2
Closed 4 months ago4
Is it possible to do fine tuning and incremental training?
Closed a year ago1
about audio_alphaca_15k.json file?
Closed 4 months ago1
Preview and save multiple samples of the same prompt
Closed 4 months ago2
Hardware.
Updated 4 months ago2
What is the proper loss value? My train and val loss is around 6.5-6.6 and do not drop.
Updated 4 months ago
License
Updated 4 months ago5
Nan loss in training
Closed a year ago5
Classifier-free guidance(CFG) in training vs inference
Closed 5 months ago1
16 GB of GPU memory runs out
Updated 5 months ago2
Reproduce result
Updated 9 months ago
About data augment
Updated 10 months ago2
Downloading AudioCaps data
Updated 10 months ago1
about tango-full-ft-audiocaps
Updated 10 months ago1
AttributeError: 'AudioDiffusion' object has no attribute 'device'
Closed 10 months ago4
Question about inference_hf.py
Updated a year ago1
Can I retrain the model on the audiocaps dataset with a 24GB 4090？
Updated a year ago
Could you provide the ChatGPT prompt of sound?
Updated a year ago1
The vae decoder cannot recover original audio with the extracted latent code
Updated a year ago1
After just using VAE reconstruct a audio, I only get noise
Updated a year ago5
Producing audio in different Sample Rate
Updated a year ago3
Can you provide your accelerate config
Closed a year ago1
Inference
Updated a year ago7
Is possible an inference with just a RTX 3080 of 10GB?
Updated a year ago3
How can I change the duration of the output audio?
Updated a year ago3
HOW MUCH VRAM IS REQUIRED FOR INFERENCE?
Closed a year ago2
The demo won't work if sentencepiece is not installed
Closed a year ago
Noisy audio samples
Closed a year ago
Training on own model
Closed a year ago2
Can this model used for music generation?
Updated a year ago3
Download Models to a Local Folder Instead of Cache Dir
Closed a year ago1
don't have a correct `repo_id` and `repo_type`?
Closed a year ago1
ImportError: cannot import name 'Tango' from 'tango' (unknown location)
Updated a year ago2
apple m1?
Closed a year ago2
Sound cloning
Updated a year ago
HF Space seems to be down?
Closed a year ago2
Inference on server without GPU
Closed a year ago2
Update Requirement infos (ipython, libsndfile1)
Closed a year ago3
encoder_attention_mask error
Closed a year ago2
Question: can we generate 1sec/ms length audio?
Closed a year ago4
Cannot install on Windows
Closed a year ago17