Matthijs Hollemans

Add support for Vision's `imageCropAndScaleOption` as an alternative for defining the crop rect by hand.

[WIP] add SpeechT5 model

12

# What does this PR do? Add the SpeechT5 model to Transformers. See also https://github.com/huggingface/transformers/issues/17569 ## Before submitting - [ ] This PR fixes a typo or improves the docs...

TTS fine-tuning for SpeechT5

2

# What does this PR do? Adds fine-tuning support for SpeechT5, in particular the TTS model. The loss function is a combination of L1 loss for the mel-spectrograms, BCE for...

audio_utils improvements

7

# What does this PR do? Recently the `audio_utils.py` file was added to Transformers to provide shared functions for audio processing such as STFT. This PR aims to clean up...

add VITS model

7

# What does this PR do? Adds the VITS model for text-to-speech, in particular to support the MMS-TTS checkpoints (which use the same model architecture but a different tokenizer). Fixes...

add new (paid) synthesizer book

2

Hi, I've added a link to my new book. Feel free to tweak the description! :smiley:

Hi there, I've added a link to my new book. Cheers!

Cannot reproduce the results from the project page

9

Hi, I was trying to run your very interesting model on the input images from the project page, but the generated IRs are always kind of the same and do...

Reels does not appear on some systems

1

 I think this may be related to the OpenGL context. The information I received from the user is: - Open GL 2 , DirectX 12 , Chipset(graphics) Intel GMA...

I messed up and added the `BinaryData.cpp` files to `git lfs` since I had expected them to be larger than they were. Turns out LFS wasn't actually needed for these...