Hmm. Really? Is it Open Source. Thanks for correcting me, I pretty much only look at open source releases so could be mistaken!
@reach_vb
-
Descript’s Audio Codec Beats Encodec: TTS Pipeline Implications
By
–
Ha! I’m assuming you considering Descript’s Audio Codec (DAC) as the current SoTA. It deffo does beat Encodec, however, I haven’t seen any OS TTS pipeline using it, hence the doubt! That said, stay tuned for more on this.. we’ve got some interesting things with DAC lined up!
-
SoTA Audio Encoding for TTS/TTA Language Modeling Pipeline
By
–
Yep! It’s SoTA/ near-SoTA atm! This serves as the key piece in a TTS/ TTA pipeline. As it allows us to encode an audio into discrete representations and then perform language modelling on it!
-
Next Generation Audio Models Development Mission
By
–
Stay tuned for more!! We’re on the mission to enable the next gen audio models!
-
Encodec: The Key Technology Behind MusicGen Audio Processing
By
–
Not quite, Encodec is part of the pipeline for MusicGen. Encodec helps with converting the audio into discrete codebook representation and back! Not as glamorous but it is the key piece behind making MusicGen as effective as it is
-
Team Adds Encodec Model in Record Time
By
–
Massive kudos to @mhollemans
, @art_zucker and patrickvonplaten for sprinting and adding this model in record time Special thanks to @honualx for all his help and support! ref: https://
github.com/facebookresear
ch/encodec
… -
Transformers Integration Enables Large-Scale Text-to-Speech Music Models
By
–
Okay, but why is it a big deal!? Transformers integration allows us to use any LM and dataset from the ecosystem seamlessly to train Text-to-Speech and Text-to-Music models at scale! More exciting announcements on this front soon! https://
github.com/Vaibhavs10/not
ebooks/blob/main/use_encodec_w_transformers.ipynb
… -
EnCodec Model Now Available in Transformers Library
By
–
Want to train your own Bark/MusicGen-like TTS/TTA models? 👀
— Vaibhav (VB) Srivastav (@reach_vb) 20 juin 2023
The SoTA Encodec model by @MetaAI has now landed in 🤗Transformers!
It supports compression up to 1.5KHz and produces discrete audio representations. ⚡️
Model: https://t.co/Hq8rDHBfjw
Colab: https://t.co/MaWVEAMCXs pic.twitter.com/tDpPAdlYHUWant to train your own Bark/MusicGen-like TTS/TTA models? The SoTA Encodec model by @MetaAI has now landed in Transformers! It supports compression up to 1.5KHz and produces discrete audio representations. Model: https://
huggingface.co/docs/transform
ers/main/en/model_doc/encodec#overview
…
Colab: https://
github.com/Vaibhavs10/not
ebooks/blob/main/use_encodec_w_transformers.ipynb
… -
Setting Up Model Repositories on Hugging Face Hub
By
–
Happy to help y’all setup your model repos on Hugging Face Hub I think the community will really benefit from this!
-
One More Fine-Tuning Run in Progress
By
–
Okay, one more fine-tuning run! https://
wandb.ai/vaibhavs10/IMS
-Toucan/runs/1pwzx4t7?workspace=user-vaibhavs10
…