We are on a mission to democratise speech, increase the language coverage of current SoTA speech recognition and push the limits of what is possible. From beginners to hobbyists to academics to power users, come one, come all! Register here: https://
forms.gle/QAkYnnSFgGb84d
UX6
…
OPEN SOURCE
-
Open Source Speech Recognition Platform Democratizing Access
By
–
-
Stable Diffusion 2.0 Shows Quality Decline Compared to 1.5
By
–
plot twist: stable diffusion 2.0 looks quite a bit worse on the few prompts i've tried so far compared to 1.5 (even not including celebrities/artists). Running theory seems to be this is due to an aggressive data sanitization campaign since the original release (?).
-
Stable Diffusion 2.0 Release Now Available on Replicate
By
–
Congrats @StabilityAI on the Stable Diffusion 2.0 release. We've got an early version to try on Replicate:
-
MineDojo: Building Open-Ended Embodied Agents Internet-Scale Knowledge
By
–
MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge Fan et al.: https://
arxiv.org/abs/2206.08853 #NeurIPS #NeurIPS2022 #ReinforcementLearning -
Data Collection Challenges and Licensing Issues in AI Projects
By
–
I think collecting the data is the major challenge. Ironically, despite the data being crowdsourced, and initially taken from someone else's repo, I believe it is against the license terms to fork that data (I am not a lawyer, so what do I know)
-
Meta Research Building Open Source AI Alternative
By
–
Maybe someone at Meta Research could be tasked with building an open source alternative? It would surely give Meta Research more prominence, containing many strong researchers and thus being near the top of the list.
-
Hugging Face Enables DreamBooth Model Creation in Five Minutes
By
–
With @huggingface now you can create a DreamBooth model in less than 5 minutes. https://
x.com/PatrickPlaten/
status/1594003815082049536?s=20&t=8vJu7SGZfKvqn_JyyqV60A
… -
Versatile Diffusion: Open-Source Multimodal AI Model Released
By
–
Versatile Diffusion can handle text-to-image, image-to-text, image-variation, and text-variation tasks. and the code is open-source! https://
github.com/SHI-Labs/Versa
tile-Diffusion
… -
Hugging Face Datasets Library Appreciation and Documentation
By
–
This is a @huggingface Datasets appreciation tweet! https://
huggingface.co/docs/datasets/
index
…