Muhammad Irfan

There is no documentation on how to use it after training the model.

Normalization and word tokenization have issues.

1

Tried to run the example given in the documentation for normalization and the results do not match. ```python normalize("پی ایس ایل میں 69 مقامی اور کرس گیل، ڈیرن سیمی، کیون...

Install requires both TensorFlow and TensorFlow-GPU? ```bash pip install urduhack[tf-gpu] ``` It seems both are required to use urduhack. ## Your Environment * Operating System: Ubuntu 18 * Python Version...

AttributeError: 'AudioProcessor' object has no attribute '_denormalize'

1

I tried to use it on my local machine and getting the following error after successfully building the docker images. ```shell [INFO] 172.17.0.1 - - [18/Mar/2021 12:19:42] "GET /api/tts?text=how%20are%20you%3F HTTP/1.1"...

Does not work on fake videos.

5

I'm trying to detect fake video and it does not work. Here is the video I'm using for fake detection https://youtu.be/r1jng79a5xc Here is output ```shell Dealing with video Jennifer Lawrence-Buscemi...

Feature type fbank_and_pitch throws error

10

I've created the `settings.ini` file to use Kaldi for feature extraction but it seems Persephone not picking up the `settings.ini` file from the directory. here is my directory structure. ```shell...

GPU support?

7

I have tried to run it with GPU but it does not work. Using TensorFlow-GPU shows import error and asks to install TensorFlow only.   How to train it...

I can't go further than this task, after successfully deploying the voice-builder server on GCP. Stuck at this point.

Is there a way we can add our own WebSocket to the app for speech recogntition?

How to use it in Python script instead of shell script.

2

Is there a way to use the model in Python script. I'm trying to do it but having lots of errors with modules importing etc.