YuanGongND/ast

Issues

• Fine tuning AST model to Music Emotion Classification Overfit

  #120 opened a year ago by moonquekes
  4

• question about normalization

  #141 opened 4 months ago by emleeee
  0

• Issue while trying to execute the Speechcommands V2 Recipe

  #140 opened 5 months ago by alexandramarkal
  1

• Install requirement issue

  #138 opened 6 months ago by Sunny-gyx
  3

• how to reproduce the same result based on my custom dataset?

  #137 opened 7 months ago by jmren168
  0

• How to incrementally fine-tune AST model with the new data?

  #136 opened 8 months ago by jmren168
  0

• AttributeError: module 'numpy.typing' has no attribute 'NDArray'

  #135 opened 8 months ago by nikhilsos
  3

• Installing requirements issues

  #123 opened a year ago by BehrouzGit
  1

• Installing requirement and CUDA on a fresh virtual environnement

  #114 opened 2 years ago by blackyx35
  1

• AssertionError: choose a window size 400 that is [2, 1]

  #133 opened 9 months ago by GrafKnusprig
  2

• Discrepancy in Model Performance Using HuggingFace Pipeline Utility

  #134 opened 9 months ago by penguinwang96825
  5

• self-contained Google Colab script error

  #129 opened a year ago by moon-aver
  2

• some questions when reproducing your results

  #131 opened 10 months ago by ben100118
  2

• csv error

  #132 opened 10 months ago by mooncv
  1

• training MAP

  #126 opened a year ago by maxwZJU
  2

• One question regarding the linear projection of AST.

  #127 opened 10 months ago by poult-lab
  1

• Ask for help

  #130 opened a year ago by Ingram-lin
  1

• Inquiry Regarding Audio Spectrogram Transformer

  #128 opened a year ago by Ingram-lin
  2

• how to use my own dataset

  #115 opened a year ago by wlssyuu
  3

• When I download the pretrained model with stride=16, I need to change `fstride` and `tstride` in the source code from 10 to 16. Besides these changes, what else do I need to adjust?

  #124 opened a year ago by zky-66
  0

• Different audio sample size for fine-tuning the model gives overfitting issue

  #125 opened a year ago by aarshilpatel
  1

• How can I adapt the pretrained AST model to fit my own dataset

  #121 opened a year ago by zky-66
  6

• ESC-50-master zip file location has changed

  #122 opened a year ago by BehrouzGit
  2

• RuntimeError: DataLoader worker (pid 39424) exited unexpectedly with exit code 1. Details are lost due to multiprocessing. Rerunning with num_workers=0 may give better error trace.

  #112 opened 2 years ago by wuhongsheng
  1

• After fine-tune a 3-class dataset, how to load its fine-tuned weighted to update pre-trained ast model?

  #118 opened a year ago by jmren168
  7

• CPU memory increase while training

  #119 opened a year ago by gudrb
  6

• seq2seq classification with AST

  #117 opened a year ago by YSLCoat
  2

• Using pretrained model for embeddings extraction with audio input samples of different durations.

  #101 opened 2 years ago by sreenivasaupadhyaya
  5

• AST Audioset Training Time and Hardware

  #116 opened a year ago by justinluong
  2

• For own data

  #113 opened 2 years ago by ShadowVicky
  1

• Huggingface-compatible ImageNet pre-trained weights

  #109 opened 2 years ago by penguinwang96825
  5

• ERROR: Cannot install -r requirements.txt (line 10)

  #111 opened 2 years ago by wuhongsheng
  1

• Regression Task

  #110 opened 2 years ago by BaMarcy
  1

• pre-processing about AudioSet (resample to 16kHz)

  #108 opened 2 years ago by wisekimm
  13

• What is the objective when pretraining?

  #107 opened 2 years ago by Young973
  3

• Multichannel Audio Input

  #106 opened 2 years ago by aaprasad
  0

• How to convert fbank tensor back to waveform?

  #105 opened 2 years ago by ebagdasa
  0

• Missing "esc_class_labels_indices.csv" file

  #104 opened 2 years ago by kaiw7
  2

• Application on ASR

  #103 opened 2 years ago by chlorane
  0

• Epoch: [4][160156/161048] training diverged...

  #102 opened 2 years ago by xiaoli1996
  3

• About AST for Speech Enhancement

  #100 opened 2 years ago by kaiw7
  5

• ast input audio length

  #99 opened 2 years ago by syjunghwang
  0

• How to use the pre-trained model on the AudioSet to extract audio features and save them as npy?

  #98 opened 2 years ago by ayameyao
  2

• Colab notebook for inference is only partly usable with CPU

  #97 opened 2 years ago by Cycerotki
  3

• SpeechCommands v2

  #94 opened 2 years ago by yunzqq
  4

• Performance issues with recorded voices

  #96 opened 2 years ago by milad-s5
  5

• In my own dataset, why is the Avg precision always 0.5 in each epoch?

  #95 opened 2 years ago by 1244547821
  1

• How to configure the dataset or modify the code if I want to do the one class binary classification

  #91 opened 2 years ago by nanyyyyyy
  14

• Training with Unbatch data!

  #93 opened 2 years ago by fallahim
  0

• Dealing with different audio lengths

  #92 opened 2 years ago by OhadCohen97
  1