Listen "Iota: whisper.cpp"
Episode Synopsis
Links:my little whisper.cpp bug fixwhy the logits were calculated inconsistentlywav2vec2 on arxiv and huggingfacethe openai whisper asr model announcementbeam search patiencetop notch guide to CTCthe bitter lesson (and in meme form)Errata:* I referred in the show to LLMs as encoder-decoder models. Most modern LLMs are decoder-only.* I messed up readability at Google. It means approvability, apparently. 🤷
More episodes of the podcast Significant Bits
Iota: Random algorithms
15/02/2024
Write It Down with Shay Nehmad
04/02/2024
Litestream and LiteFS with Ben Johnson
22/01/2024
Iota: Rolling Hashes and FastCDC
30/12/2023
Trailer
25/11/2023
ZARZA We are Zarza, the prestigious firm behind major projects in information technology.