auto_avsr

auto_avsr copied to clipboard

Hello, thank you for sharing the code. I would like to repeat your work first. May I ask under what equipment does this code run and how long has it...

white1-doggy

Problems with data processing using a self-built dataset

1

Thank you very much for your work. When I used [https://github.com/mpc001/auto_avsr/blob/main/INSTRUCTION.md](url) process my own dataset, an offset occurred. What could be the reason for this? The detector used is mediapipe....

YuQing2000

Hello, I noticed that the text information in the LRS3 dataset contains timestamps. What is the main use of these timestamps? Are they used in training? If I want to...

YuQing2000

Running Demo gets ModuleNotFoundError: No module named 'six'

5

I've tried to run demo with a video for vsr executing the next line: ``` (TT) PS D:\auto_avsr> python demo.py data.modality='audio' pretrained_model_path='.\asr_trlrs3vox2_base.pth' file_path='.\avsr_english_1.mp4' ``` but i got the next error...

M1ndBlast

Dear author, after conducting unimodal training on video information, I obtained some models. I want to test them for alignment, but during the testing process, I found the following issues:...

zhiishuo

Thank you for sharing the code. I am interested in training VSR model (lip_reading) for digit recognition using grid dataset. because the pre-train weights are not perfectly working for digits...

Chhaya-Trootech

I noticed that there isn't a location to download the videos of the AVSpeech dataset. I understand that you likely took the time to download the videos, trim them, label...

shadtorrie

Hydra Conflict Problem

6

Hi Thank you for sharing the code. For Installing additional packages in step 3.4 I got this error: ERROR: pip's dependency resolver does not currently take into account all the...

SarahSalimpour

cannot import name 'eval_env' from 'torchaudio._internal.module_utils'

1

When I run: `python train.py exp_dir=D:/pycharmProject/auto_avsr-main/auto_avsr-main/checkpoints exp_name=exp1 data.modality=video data.dataset.root_dir=D:/BaiduNetdiskDownload/pre ` I got this error: `Traceback (most recent call last): File "train.py", line 10, in from datamodule.data_module import DataModule File "D:\pycharmProject\auto_avsr-main\auto_avsr-main\datamodule\data_module.py",...

YuQing2000

Re-implementation error

1

Does the problem previously posed as a question(https://github.com/mpc001/auto_avsr/issues/20) affect performance? I'm re-training with a newly updated code. Here, as a question, I'm using A100 GPUs(4) to perform training, so I'm...

jeonhuhuhu