Simple colab to measure different ASR models
https://colab.research.google.com/drive/10lVRC-zLtZ2q60x_VpnqsKerFiavwG6b?usp=sharing
#asr
https://colab.research.google.com/drive/10lVRC-zLtZ2q60x_VpnqsKerFiavwG6b?usp=sharing
#asr
Google
Evaluate ASR results from a file.ipynb
Colab notebook
Forwarded from Feed-Master
Prossimo
Porting C to Rust for a Fast and Safe AV1 Media Decoder
AV1 is an increasingly important video format and it needs a memory safe, high performance decoder. We worked with the team at Immunant to develop rav1d, a Rust-based port of dav1d, a C decoder. This is the first of two blog posts about how the team approached…
Forwarded from Feed-Master
GitHub
GitHub - lakehq/sail: Drop-in Apache Spark replacement written in Rust, unifying batch processing, stream processing, and compute…
Drop-in Apache Spark replacement written in Rust, unifying batch processing, stream processing, and compute-intensive AI workloads. - lakehq/sail
Forwarded from Yehor Smoliakov
Forwarded from Hacker News
Tutorial on diffusion models for imaging and vision (Score: 150+ in 11 hours)
Link: https://readhacker.news/s/6ekYF
Comments: https://readhacker.news/c/6ekYF
Link: https://readhacker.news/s/6ekYF
Comments: https://readhacker.news/c/6ekYF
arXiv.org
Tutorial on Diffusion Models for Imaging and Vision
The astonishing growth of generative tools in recent years has empowered many exciting applications in text-to-image generation and text-to-video generation. The underlying principle behind these...
Just use a faster tokenizer in
https://github.com/egorsmkv/optimized-whisper/issues/2
#asr #ai
transformershttps://github.com/egorsmkv/optimized-whisper/issues/2
#asr #ai
Scraping website with LLMs
https://jina.ai/news/reader-lm-small-language-models-for-cleaning-and-converting-html-to-markdown/?nocache=1
#llm #nlp #ai
https://jina.ai/news/reader-lm-small-language-models-for-cleaning-and-converting-html-to-markdown/?nocache=1
#llm #nlp #ai
jina.ai
Reader-LM: Small Language Models for Cleaning and Converting HTML to Markdown
Reader-LM-0.5B and Reader-LM-1.5B are two novel small language models inspired by Jina Reader, designed to convert raw, noisy HTML from the open web into clean markdown.