declare-lab/tango

Issues

• FAD in Tango and Tango 2

  #58 opened 2 months ago by jacklishufan
  0

• length of generated sounds

  #57 opened 2 months ago by Janbinco
  0

• Trouble Installing the Required PyTorch Version

  #56 opened 3 months ago by joshua-beck-0908
  3

• FileNotFoundError: [Errno 2] No such file or directory: '/home/karen/.cache/audioldm/audioldm-s-full.ckpt'

  #55 opened 3 months ago by VinceAlle
  1

• How to solve this error：requests.exceptions.ProxyError: HTTPSConnectionPool(host='huggingface.co', port=443)

  #54 opened 4 months ago by 2023210549
  1

• How did you split the MusicCaps dataset into training and testing sets?

  #53 opened 5 months ago by hongming21
  0

• laugh

  #52 opened 6 months ago by molmaryn
  0

• Evaluation Protocol

  #51 opened 7 months ago by MoayedHajiAli
  2

• Fine-Tuning TANGO 2

  #50 opened 8 months ago by cvillela
  4

• Is it possible to do fine tuning and incremental training?

  #32 opened a year ago by fyell
  1

• about audio_alphaca_15k.json file?

  #48 opened 8 months ago by wanghua-lei
  1

• Preview and save multiple samples of the same prompt

  #45 opened 8 months ago by esuriddick
  2

• Hardware.

  #41 opened 10 months ago by arthurwolf
  2

• What is the proper loss value? My train and val loss is around 6.5-6.6 and do not drop.

  #46 opened 8 months ago by BingliangLi
  0

• License

  #40 opened a year ago by fakerybakery
  5

• Nan loss in training

  #17 opened 2 years ago by tranquangchung
  5

• Classifier-free guidance(CFG) in training vs inference

  #42 opened 9 months ago by sakshamsingh1
  1

• 16 GB of GPU memory runs out

  #18 opened 2 years ago by itsmasabdi
  2

• Reproduce result

  #39 opened a year ago by vtnhan1309
  0

• About data augment

  #38 opened a year ago by Catekato
  2

• Downloading AudioCaps data

  #36 opened a year ago by fyell
  1

• about tango-full-ft-audiocaps

  #37 opened a year ago by Yusiissy
  1

• AttributeError: 'AudioDiffusion' object has no attribute 'device'

  #35 opened a year ago by fyell
  4

• Question about inference_hf.py

  #34 opened a year ago by RookieJunChen
  1

• Can I retrain the model on the audiocaps dataset with a 24GB 4090？

  #33 opened a year ago by 525qqqqq
  0

• Could you provide the ChatGPT prompt of sound?

  #31 opened a year ago by LinB203
  1

• The vae decoder cannot recover original audio with the extracted latent code

  #30 opened a year ago by ikm565
  1

• After just using VAE reconstruct a audio, I only get noise

  #19 opened 2 years ago by SuperiorDtj
  5

• Producing audio in different Sample Rate

  #29 opened a year ago by cvillela
  3

• Can you provide your accelerate config

  #14 opened a year ago by 965694547
  1

• Inference

  #28 opened a year ago by voicegen
  7

• Is possible an inference with just a RTX 3080 of 10GB?

  #25 opened 2 years ago by davidmartinrius
  3

• How can I change the duration of the output audio?

  #21 opened 2 years ago by ChloeL19
  3

• HOW MUCH VRAM IS REQUIRED FOR INFERENCE?

  #27 opened a year ago by illtellyoulater
  2

• The demo won't work if sentencepiece is not installed

  #24 opened 2 years ago by davidmartinrius
  0

• Noisy audio samples

  #22 opened 2 years ago by schowdhury671
  0

• Training on own model

  #16 opened 2 years ago by ciuhc
  2

• Can this model used for music generation?

  #15 opened 2 years ago by gandolfxu
  3

• Download Models to a Local Folder Instead of Cache Dir

  #9 opened 2 years ago by HansRandomizer
  1

• don't have a correct `repo_id` and `repo_type`?

  #6 opened 2 years ago by EveningLin
  1

• ImportError: cannot import name 'Tango' from 'tango' (unknown location)

  #13 opened 2 years ago by tralala87
  2

• apple m1?

  #12 opened 2 years ago by iamcos
  2

• Sound cloning

  #11 opened 2 years ago by darkman111a
  0

• HF Space seems to be down?

  #4 opened 2 years ago by regstuff
  2

• Inference on server without GPU

  #8 opened 2 years ago by trholding
  2

• Update Requirement infos (ipython, libsndfile1)

  #7 opened 2 years ago by HansRandomizer
  3

• encoder_attention_mask error

  #5 opened 2 years ago by kotaxyz
  2

• Question: can we generate 1sec/ms length audio?

  #3 opened 2 years ago by wassimbj
  4

• Cannot install on Windows

  #1 opened 2 years ago by SoftologyPro
  17