Day 3 of Whisper Fine Tuning Sprint powered by @LambdaAPI
! Our community is operating at lightning speed! So far we've added:
– 51 Whisper checkpoints
– 20+ languages https://
huggingface.co/models?other=w
hisper-event
… Here are some awesome contributions from the community
OPEN SOURCE
-
Whisper Fine Tuning Sprint Achieves 51 Checkpoints Across 20 Languages
By
–
-
Spanish Whisper Medium Model Fine-tuned Achieves 5.4% Error Rate
By
–
Whisper medium checkpoint fine-tuned on Spanish with a WER of 5.4218 by @juancopi81 https://
huggingface.co/juancopi81/whi
sper-medium-es
… -
LangChain Mid-Week Release: Community Updates and Future Discussions
By
–
Thanks to all for a surprisingly big mid-week release! Lots is happening. Check out the GitHub or Discord to stay up to date + help discuss future ideas GitHub: https://
github.com/hwchase17/lang
chain
… Discord: https://
discord.gg/6adMQxSpJS -
LangChain Adds Bash Utility and Natural Language to Command Chain
By
–
@coyotespike added a Bash utility (a wrapper on subprocess) He then also added a chain to convert natural language to a bash command. Very useful for interacting with the terminal! See the example here: https://
langchain.readthedocs.io/en/latest/exam
ples/chains/llm_bash.html
… -
LangChain 0.0.31 Release: New Agents, Bash, and Chains
By
–
LangChain version 0.0.31 @johnvmcdonnell fixed how Agents handle a missing tool (so no longer errors) Bash utility and a LLMBashChain (
@coyotespike
) a generic transformation chain (
@AkashSamant4
) a requests chain (
@BruceHammer
) on these additions: -
Open-source ecosystem growth: timm, diffusers, evaluate, skops
By
–
The open-source ecosystem has grown a lot this year: timm joined us, diffusers, evaluate, and skops were born. How can we do better? If you're a user of our open-source libraries, we'd love you to answer the survey for a badge on GitHub & HF: https://
forms.gle/TTTJJWVUHX1VDM
YX9
… -
PLATO-K: Chinese dialogue model achieves new SOTA performance
By
–
Introducing PLATO-K, a 22B Chinese open-domain dialogue generation model with knowledge enhancement. PLATO-K achieves new SOTA in Chinese open-domain conversation with remarkable improvements in knowledge accuracy and overall engagingness. Paper: https://
arxiv.org/abs/2211.00910 -
Stable Diffusion 1.5 Version 27b93a2 Still Available on Replicate
By
–
Stable Diffusion 1.5 is still on Replicate. If you want to keep on using it, use version 27b93a2:
-
Stable Diffusion 2.0 Release Blog Post Announcement
By
–
To learn more about Stable Diffusion 2.0, take a look at @stabilityai
's blog post: https://
stability.ai/blog/stable-di
ffusion-v2-release
… -
Stable Diffusion 2.0 launches on Replicate with enhanced capabilities
By
–
Stable Diffusion 2.0 is now on Replicate. It has a completely new text encoder developed by @laion_ai and can natively generate images at 768×768 pixels. https://
replicate.com/stability-ai/s
table-diffusion
…