Pegah Salehi

Error related to "align_68.py" file

2

Thank you for your excellent work! After running the "align_68.py" file, I first encountered an error [ZeroDivisionError: division by zero], after fixing it. The code is executed but no file...

How can we extract the logits from audio?

1

Is there anyone who uses whisper-jax to extract logits from audio?

I can't run the demo because of these two warnings that I put here. Please help me !python inference.py \ --config configs/inference.yaml \ --video_source=./docs/demo/videos/RD_Radio34_003_512.mp4 \ --output_dir=./docs/demo/output --if_extract ___________________________________________________________________________________________________ `model [FaceReconModel]...

What is the meaning of implementing by C++?

1

Hi @YuanxunLu I run `demo.py` with RTX3080, it takes about 1 minute. Is the implementation of real-time related to this sentence in the paper? **We implement and test our real-time...

Real-time execution

3

The process of generating the video in Google Colab takes one minute, despite the fact that it is real-time. Why is this the case?

Running the code in stream mode

2

How can we have a stream using `asr.py` ? So that the audio file does not need to be input as a file. For example, my words can be repeated...

NoneType' object is not subscriptable

4

Thanks for this great work! After I run `python data_utils/process.py data/obama/obama.mp4`, I faced this error: ``` ImportError: cannot import name 'PILLOW_VERSION' from 'PIL' (/usr/local/lib/python3.7/site-packages/PIL/__init__.py) [INFO] ===== extracted semantics ===== [INFO]...

No such file or directory: track_params.pt

6

``` Output #0, image2, to 'data/obama/ori_imgs/%d.jpg': Metadata: major_brand : isom minor_version : 512 compatible_brands: isomiso2avc1mp41 date : 2021/06/24 23:54:51 encoder : Lavf57.83.100 Stream #0:0(und): Video: mjpeg, yuvj420p(pc), 450x450 [SAR 1:1...

bash scripts/install_ext.sh in Windows

11

Hi @ashawkey Is it possible to install these libraries on Windows? ``` pip install ./freqencoder pip install ./shencoder pip install ./gridencoder pip install ./raymarching ``` Thanks in advance for your...

using another audio feature extraction

16

During testing, I plan to use another audio feature extraction with a different shape (x, 16, 80). But it is incompatible with the convolution model. `RuntimeError: Given groups=1, weight of...