YuanGongND ast issues - Githubissues

YuanGongND / ast

Code for the Interspeech 2021 paper "AST: Audio Spectrogram Transformer".

BSD 3-Clause "New" or "Revised" License

1.06k stars 203 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Discrepancy in Model Performance Using HuggingFace Pipeline Utility

#134 penguinwang96825 opened 1 week ago
5
AssertionError: choose a window size 400 that is [2, 1]

#133 GrafKnusprig opened 1 week ago
2
csv error

#132 mooncv opened 1 month ago
1
some questions when reproducing your results

#131 ben100118 opened 1 month ago
2
Ask for help

#130 Ingram-lin opened 1 month ago
1
self-contained Google Colab script error

#129 moon-aver opened 2 months ago
2
Inquiry Regarding Audio Spectrogram Transformer

#128 Ingram-lin opened 2 months ago
2
One question regarding the linear projection of AST.

#127 poult-lab closed 3 weeks ago
1
training MAP

#126 maxwZJU opened 3 months ago
2
Different audio sample size for fine-tuning the model gives overfitting issue

#125 aarshilpatel closed 3 months ago
1
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 zky-66 closed 3 months ago
0
Installing requirements issues

#123 BehrouzGit opened 3 months ago
0
ESC-50-master zip file location has changed

#122 BehrouzGit closed 3 months ago
2
How can I adapt the pretrained AST model to fit my own dataset

#121 zky-66 closed 3 months ago
6
Fine tuning AST model to Music Emotion Classification Overfit

#120 moonquekes opened 5 months ago
2
CPU memory increase while training

#119 gudrb opened 5 months ago
6
After fine-tune a 3-class dataset, how to load its fine-tuned weighted to update pre-trained ast model?

#118 jmren168 opened 5 months ago
7
seq2seq classification with AST

#117 YSLCoat opened 7 months ago
2
AST Audioset Training Time and Hardware

#116 justinluong closed 8 months ago
2
how to use my own dataset

#115 wlssyuu opened 9 months ago
3
Installing requirement and CUDA on a fresh virtual environnement

#114 blackyx35 opened 9 months ago
1
For own data

#113 ShadowVicky opened 9 months ago
1
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 wuhongsheng opened 10 months ago
1
ERROR: Cannot install -r requirements.txt (line 10)

#111 wuhongsheng closed 10 months ago
1
Regression Task

#110 BaMarcy opened 10 months ago
1
Huggingface-compatible ImageNet pre-trained weights

#109 penguinwang96825 closed 9 months ago
5
pre-processing about AudioSet (resample to 16kHz)

#108 wisekimm opened 11 months ago
13
What is the objective when pretraining?

#107 Young973 opened 11 months ago
3
Multichannel Audio Input

#106 aaprasad opened 12 months ago
0
How to convert fbank tensor back to waveform?

#105 ebagdasa opened 1 year ago
0
Missing "esc_class_labels_indices.csv" file

#104 kaiw7 closed 1 year ago
2
Application on ASR

#103 chlorane opened 1 year ago
0
Epoch: [4][160156/161048] training diverged...

#102 xiaoli1996 opened 1 year ago
3
Using pretrained model for embeddings extraction with audio input samples of different durations.

#101 sreenivasaupadhyaya opened 1 year ago
5
About AST for Speech Enhancement

#100 kaiw7 opened 1 year ago
5
ast input audio length

#99 syjunghwang closed 1 year ago
0
How to use the pre-trained model on the AudioSet to extract audio features and save them as npy?

#98 ayameyao opened 1 year ago
2
Colab notebook for inference is only partly usable with CPU

#97 Cycerotki opened 1 year ago
3
Performance issues with recorded voices

#96 milad-s5 opened 1 year ago
5
In my own dataset, why is the Avg precision always 0.5 in each epoch?

#95 1244547821 opened 1 year ago
1
SpeechCommands v2

#94 yunzqq opened 1 year ago
4
Training with Unbatch data!

#93 fallahim opened 1 year ago
0
Dealing with different audio lengths

#92 OhadCohen97 opened 1 year ago
1
How to configure the dataset or modify the code if I want to do the one class binary classification

#91 nanyyyyyy opened 1 year ago
14
Can AST be used for audio representation towards solving the frame-level classification tasks?

#90 SylviaZiyaZhou opened 1 year ago
4
Cannot create a file when that file already exists: './exp/test-esc50-f10-t10-impTrue-aspTrue-b48-lr1e-5/fold1/models'

#89 JonathanFL closed 1 year ago
4
About code"100-106" from dataloader.py

#88 poult-lab opened 1 year ago
6
Audio length 1s

#87 9B8DY6 closed 1 year ago
5
Q: Audio-MAE reports that AST's performance on VoxCeleb1 is 41.1%, but not listed on the AST paper

#86 daisukelab closed 1 year ago
2
The problem of reproducing the AST result in full dataset

#85 MichaelLynn1996 opened 1 year ago
9