In my experience those results were quite suboptimal and didn’t quite result in usable transcriptions. With better decoding strategy those issues can be alleviated a bit. So the hack is more so of using contrastive search with Whisper to enable such use cases. Will run more
OPEN SOURCE
-
Fine-Tuning Whisper Model for Improved Performance
By
–
Definitely yes! You can fine-tune Whisper to boost the model performance: https://
huggingface.co/blog/fine-tune
-whisper
… -
KerasCV Marine Animal Detection in Photos and Videos
By
–
Detect marine animals in photos and videos with KerasCV: https://
lukewood.xyz/blog/marine-an
imal-detection
… By @luke_wood_ml -
LangChain 101: Build GPT-Powered NLP Applications
By
–
LangChain is a Python library that helps you leverage large language models to build custom NLP applications. In this guide, we’ll explore what LangChain is and what you can build with it. LangChain 101: Build Your Own GPT-Powered Applications https://
bit.ly/41HgC35 -
Cerebras Tech Talk: SlimPajama Open-Source LLM Dataset
By
–
Cerebras Tech Talk this Wednesday! On June 28th at 11:00 AM PT, we will discuss how we created SlimPajama, the largest deduplicated, multi-corpora, open-source dataset for training large language models Register for this 30-minute interactive Q&A here: https://
hubs.li/Q01VRMFY0 -
Contrastive Search Benchmarks Coming Soon for Developers
By
–
Definitely! More benchmarks on contrastive search coming soon too Thanks for empowering millions of developers
-
Open Source Models Now Support Custom Tokenizer Fallbacks
By
–
Of course, when using an open source model (Vicuna, Dolly) that model name is not in the tiktoken wrapper Previously, this would raise an error We've now updated this to: (1) fallback to a default tokenizer, (2) allow users to specify model name to use for tiktoken
-
LangChain PR improves open source model experimentation
By
–
PR for this here: https://
github.com/hwchase17/lang
chain/commit/e9877ea8b1d301efafb7d2fda5f9105b005774b8
… Shout out to Yuze Ma for highlighting this limitation at a hackathon this weekend! Hopefully this should make it easier to experiment with open source models -
Open Source Model APIs Now OpenAI-Compatible via LangChain
By
–
Many startups focused on serving open source models have exposed APIs that are interoperable with OpenAI This makes it easy for anyone to try them out by just changing the API base We added better support for this in @langchain in the most recent release (h/t Yuze Ma)
-
LangChain API Base Configuration and Token Management
By
–
It's always been possible to change the API base in the LangChain model wrappers However, the model wrappers do a lot of handy things like token management, which rely on tokenizers that by default we look up in tiktoken We look this up based on model name