Joshua Lochner

> @ArthurZucker I believe it is the opposite, the mismatch happens when ftfy is not installed. (@connor-henderson correct me if I misunderstood your posts). Yes, this is correct. I don't...

Commenting to mark as not stale :)

Commenting to prevent it being closed as stale.

> Hey, I'd be more than happy to take up this task if we can decide on the other 1-2 models We can probably just select the most popular models...

> Hey, I'd be more than happy to take up this task if we can decide on the other 1-2 models Let me know if you need any help! I’m...

Here's another model which could fall into the `text-to-speech` category: https://github.com/huggingface/transformers/issues/23036

Good news! This is currently being worked on: https://github.com/huggingface/transformers/pull/24952 🚀🔥

Hi there 👋 You should be able to export the model without `--optimize O1`. Is the O1 optimization necessary for your use-case? ```sh $ optimum-cli export onnx --model MIT/ast-finetuned-audioset-10-10-0.4593 out...

@fxmarty I'd be interested in adding this to transformers.js - do you think it's worth revisiting?

100% agree with @josephrocca. 4-bit quantization would be massive for my [Transformers.js](https://github.com/xenova/transformers.js) library (and other WebML libraries)!