LLMS - AI Dynamics

Fine-tuned Whisper Model Achieves Breakthrough Northern Sami Language Support

By

–

15 December 2022 19h05

Saved the special one for the last! Northern Sami language – A language that is not even supported by the Whisper model. @versae
's fine-tuned Whisper large checkpoint gets an astounding 24.55 Model:

→ View original post on X — @reach_vb

15 December 2022

Fine-tuned Whisper Model Achieves Impressive Greek Speech Recognition

By

@reach_vb

–

15 December 2022 19h05

Now for some high-resource languages,
Greek @4re3d0m
's fine-tuned Whisper large checkpoint gets an impressive 10.14 WER when compared to 16 (large) Model: https://
huggingface.co/emilios/whispe
r-large-v2-el-c2
…

→ View original post on X — @reach_vb

15 December 2022

Fine-tuned Whisper Model Achieves 17.8 WER for Latvian

By

@reach_vb

–

15 December 2022 19h05

Latvian @anuragcomm
's fine-tuned Whisper large checkpoint gets an impressive WER of 17.8 when compared to 25.5 by the large checkpoint! Model:

→ View original post on X — @reach_vb

15 December 2022

Lithuanian Whisper Model Achieves Major WER Improvement

By

@reach_vb

–

15 December 2022 19h05

Lithuanian @DeividasMat
's fine-tuned Whisper medium checkpoint managed to get the WER down from 35.2 (large) -> 20.44 Model:

→ View original post on X — @reach_vb

15 December 2022

ChatGPT tweets liked by Elon Musk curated

By

@perplexity_ai

–

15 December 2022 18h27

Filter down to content you’re curious about:
"tweets about chatGPT liked by Elon Musk" https://
perplexity.ai/sql?uuid=0a675
88c-2ecb-4696-88cf-4aa321cf3a96
…

→ View original post on X — @perplexity_ai

15 December 2022

ERNIE-Code: Unified Multilingual Code-to-Text Model

By

@baiduresearch

–

15 December 2022 18h00

Introducing ERNIE-Code, a unified pre-trained language model for 116 natural languages and 6 programming languages. ERNIE-Code outperforms previous models for multilingual code-to-text, text-to-code, code-to-code, and text-to-text generation. Paper: https://
arxiv.org/abs/2212.06742

→ View original post on X — @baiduresearch

15 December 2022

LangChain Enables LLM Caching with Three Lines of Code

By

@langchain

–

15 December 2022 17h37

Caching now enabled With 3 lines of code, you can now enable caching for all LLM calls This makes it cheaper and easier to experiment with changing only parts of a chain Supports both a temporary InMemoryCache, as well as a persistent SQLiteCache

→ View original post on X — @langchain

15 December 2022

LangChain v0.0.38: New LLM Caching Feature Released

By

@langchain

–

15 December 2022 17h37

New in v0.0.38 Read more about this here: https://
langchain.readthedocs.io/en/latest/exam
ples/prompts/llm_functionality.html#Caching
… @AkashSamant4 for making LLM configurations serializable, a prerequisite for this @brucehammer and @DannyHabibs for highlighting this as a valuable feature

→ View original post on X — @langchain

15 December 2022

AI Technology: Powerful but Not Human Intelligence

By

@inma_martinez

–

15 December 2022 17h12

It has been “fed” thousands of documents up to 2021 so that you can ask about a given topic and be given a simple answer. Yes it can write in poetic form or write a one pager on climate change but it is #nothuman

→ View original post on X — @inma_martinez

15 December 2022