haoheliu/AudioLDM-training-finetuning

Issues

• what inside of dataset file ? i dont have that much size on hardisk

  #41 opened 6 months ago by xalteropsx
  6

• cannot download checkpoints

  #49 opened 18 days ago by Sensorymagicia
  0

• Requirements

  #48 opened 24 days ago by mateusztobiasz
  1

• 48 kHz HiFiGAN training data

  #47 opened 2 months ago by philgzl
  0

• About the released code

  #45 opened 4 months ago by CJ416
  2

• Is it Necessary to Train CLAP Alongside LDM and VAE for my own Data?

  #46 opened 4 months ago by songbh56
  2

• I can't see the printed logs during training

  #44 opened 5 months ago by Ask-sola
  1

• GPT2 training

  #5 opened a year ago by ivcy0928
  1

• Fatal issue occurred during fine-tuning.

  #43 opened 5 months ago by Ask-sola
  3

• Question on reproduction of AudioLDM training

  #42 opened 5 months ago by aFewThings
  0

• Training weights and pipeline LDM2

  #40 opened 6 months ago by Tortoise17
  0

• clap architecture

  #39 opened 6 months ago by hananetli
  0

• Poetry install is taking a long time while installing dependencies

  #35 opened 7 months ago by supernirmesh
  1

• Pretrained VAE License

  #37 opened 7 months ago by VedantKalbag
  0

• training audioldm1 and not audioldm2

  #36 opened 7 months ago by kmaro2345
  2

• Training Code for AudioLDM2

  #24 opened a year ago by Tortoise17
  5

• error in saved checkpoints

  #34 opened 7 months ago by userpspsname12
  2

• infer trained ldm

  #33 opened 7 months ago by netagl
  0

• Training on our own dataset.

  #2 opened a year ago by Praniyendeev
  6

• clap_htsat_tiny.pt is not avaiable in checkpoint.tar

  #17 opened a year ago by ntqnhanguyen
  5

• train AudioLDM from beginning to end

  #32 opened 8 months ago by Linghuxc
  0

• Cosine scheduler gives much worse results

  #31 opened 9 months ago by MoayedHajiAli
  0

• Purpose of extra_sa_layer

  #30 opened 9 months ago by nikifori
  0

• AudioLDM-M-full vs AudioLDM-L-full

  #29 opened 10 months ago by nikifori
  0

• Finetune on a hugging face checkpoint

  #28 opened a year ago by yangqing-20
  0

• Generating longer audio sequences.

  #27 opened a year ago by Praniyendeev
  0

• Some question regarding the Training

  #26 opened a year ago by Respaired
  0

• class_labels_indices.csv generation

  #25 opened a year ago by lamHoussam
  0

• Embed mode for AudioLDM model

  #23 opened a year ago by NZqian
  0

• Inference is very slow

  #22 opened a year ago by DucHuyAnalyst
  0

• How to define time of an audio

  #13 opened a year ago by huutuongtu
  1

• A question about training with transcription

  #19 opened a year ago by wangjs9
  7

• About configuration of released code and model

  #6 opened a year ago by VanderHua
  1

• question about the metadata

  #18 opened a year ago by holehole5566
  2

• Use pretrained model on 32kHz dataset to fintune on 16kHz dataset

  #16 opened a year ago by qbKhanh
  1

• Support LoRA finetuning in the future?

  #15 opened a year ago by ZhengJun-AI
  1

• Unable to infer model in latest release. Please, help me!!

  #14 opened a year ago by manhdoan291
  0

• Inference code

  #4 opened a year ago by anhquannguyen21
  3

• How to inference model ? Please

  #7 opened a year ago by manhdoan291
  2