Kamil Akesbi

[WIP] - Using assistant in AutomaticSpeechRecognitionPipeline with different encoder size

3

This PR aims at fixing issue #30611: - First: an error will be thrown if the assistant and main models encoders don't have the same size, and the assistant is...

Add Push to Hub functionnality to Model and Pipeline

4

Hi @hbredin, I've started working on adding a `push_to_hub` method to both Model and Pipeline classes. It will hopefully help users push their custom pyannote speaker-segmentation and speaker-embedding models to...

[WIP] - Support generating with fallback for short form audio in Whisper

1

# What does this PR do? The aim of this PR is to refacto the Whisper `generate` method to handle both short form and long form audio generation similarly. It...

Add Descript-Audio-Codec model

5

# What does this PR do? This PR aims at adding [Descript-Audio-Codec model](https://github.com/descriptinc/descript-audio-codec/tree/main), a high fidelity general neural audio codec, to the Transformers library. This model is composed of 3...

Add Microsoft CLAP model

4

## What does this PR do ? This PR aims at adding the [Microsoft CLAP](https://github.com/microsoft/CLAP/tree/main) (MSClap) model to Transformers. The architecture can be decomposed in two parts: The first part...