paper page: https://
huggingface.co/papers/2305.13
516
…
@_akhaliq
-
Documentation of MMS Transformers on Hugging Face
By
–
docs: https://huggingface.co/docs/transformers/main/en/model_doc/mms
-
Fine-tuning MMS Adapters on Hugging Face
By
–
fine-tuning: https://
huggingface.co/blog/mms_adapt
ers
… -
Meta AI Scales Speech Technology to Over 1000 Languages
By
–
Meta AI released Scaling Speech Technology to 1,000+ Languages
— AK (@_akhaliq) 21 juin 2023
demo: https://t.co/1yMek3Uzbl
Expanding the language coverage of speech technology has the potential to improve access to information for many more people. However, current speech technology is restricted to about… pic.twitter.com/BHmA7J5YnWMeta AI released Scaling Speech Technology to 1,000+ Languages demo: https://
huggingface.co/spaces/mms-met
a/MMS
… Expanding the language coverage of speech technology has the potential to improve access to information for many more people. However, current speech technology is restricted to about -
Disney Characters Transformed into Cyberpunk Style by Midjourney
By
–
Disney Characters Transformed into Cyberpunk Style, midjourney AI 1. Mickey Mouse
-
Multitrack Music Transcription with Time-Frequency Perceiver
By
–
Multitrack Music Transcription with a Time-Frequency Perceiver paper page: https://
huggingface.co/papers/2306.10
785
… Multitrack music transcription aims to transcribe a music audio input into the musical notes of multiple instruments simultaneously. It is a very challenging task that typically -
RoboCat: Self-Improving Foundation Agent for Robotic Manipulation
By
–
RoboCat: A Self-Improving Foundation Agent for Robotic Manipulation paper page: https://
huggingface.co/papers/2306.11
706
… The ability to leverage heterogeneous robotic experience from different robots and tasks to quickly master novel skills and embodiments has the potential to transform robot -
MotionGPT: Finetuned LLMs for General-Purpose Motion Generation
By
–
MotionGPT: Finetuned LLMs are General-Purpose Motion Generators
— AK (@_akhaliq) 21 juin 2023
paper page: https://t.co/FJM2YqZwHR
Generating realistic human motion from given action descriptions has experienced significant advancements because of the emerging requirement of digital humans. While recent… pic.twitter.com/DgUkKy7T7rMotionGPT: Finetuned LLMs are General-Purpose Motion Generators paper page: https://
huggingface.co/papers/2306.10
900
… Generating realistic human motion from given action descriptions has experienced significant advancements because of the emerging requirement of digital humans. While recent -
Diffusion Models for Solving Inverse Problems Without Supervision
By
–
Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision paper page: https://
huggingface.co/papers/2306.11
719
… Denoising diffusion models are a powerful type of generative models used to capture complex distributions of real-world signals. However, their -
HomeRobot: Open-Vocabulary Mobile Manipulation for Object Picking
By
–
HomeRobot: Open-Vocabulary Mobile Manipulation
— AK (@_akhaliq) 21 juin 2023
paper page: https://t.co/Bg5DY8snQ8
Open-Vocabulary Mobile Manipulation (OVMM) is the problem of picking any object in any unseen environment, and placing it in a commanded location. This is a foundational challenge for robots to… pic.twitter.com/J4atienxw2HomeRobot: Open-Vocabulary Mobile Manipulation paper page: https://
huggingface.co/papers/2306.11
565
… Open-Vocabulary Mobile Manipulation (OVMM) is the problem of picking any object in any unseen environment, and placing it in a commanded location. This is a foundational challenge for robots to