Fix Requirements, Add Colab

[nivibilla]

Hi,

I just ran your code, and fixed some stuff(attrdict and espeak-ng were missing in the setup). I also made a colab notebook for the LJSpeech model inference.

Thanks

[yl4579]

Thanks for fixing the requirements. However, your Colab notebook doesn't really work because you didn't actually download the pre-trained models. Instead, you copied them from your Google Drive. You can use gdown --id GOOGLE_DRIVE_ID to download these files directly in the Colab notebook from your Google Drive once you have shared them. Once you have fixed it I can merge it into the main branch. Thank you for your help.

[nivibilla]

Ah right, I didn't know that. Will fix it. Thanks.

[nivibilla]

Changed to gdown, added colab file to demo folder

[nivibilla]

@yl4579 pls review.

[satani99]

Hi, @nivibilla are you able to run Emotional Speech Synthesis from https://styletts.github.io/ . Like prosody cloning.

[nivibilla]

@satani99 yes it uses the sample audio as reference.

[nivibilla]

You can add your own audio as reference with different emotions and do the prosody cloning.

[satani99]

Where do I get code for inference @nivibilla ?

[nivibilla]

https://colab.research.google.com/drive/18xNehSLiClZC3ub3eXiPCOnR4bz3r5Ur?usp=sharing

[satani99]

Thank you