forks/candle.git -

	Commit message (Expand)	Author	Age	Files	Lines
*	Fix bug in whisper transformer (#2681)	mert-kurttutan	2024-12-24	1	-0/+1
*	Module Docs (#2624)	zachcp	2024-11-18	1	-3/+7
*	Documentation Pass for Models (#2617)	zachcp	2024-11-15	1	-0/+8
*	Clippy fixes for 1.81.0. (#2461)	Laurent Mazare	2024-09-05	1	-2/+2
*	Speaker embeddings computation for metavoice. (#1800)	Laurent Mazare	2024-03-04	1	-1/+1
*	feat: support microphone whisper streaming (#1678)	drbh	2024-02-12	2	-0/+53
*	feat: support multithread spectrogram and small perf tweaks (#1674)	drbh	2024-02-08	3	-28/+150
*	Use candle_nn::embedding instead of local copies in a few models. (#1562)	Jani Monoses	2024-01-10	1	-6/+1
*	Use the whisper-v3 tokenizer now that it has been added. (#1337)	Laurent Mazare	2023-11-16	1	-1/+1
*	fix: address clippy 0.1.74 issues (#1336)	drbh	2023-11-16	1	-2/+1
*	Preliminary support for whisper v3. (#1294)	Laurent Mazare	2023-11-08	2	-3/+7
*	Consolidate the with-tracing usage. (#1234)	Laurent Mazare	2023-11-01	1	-27/+1
*	Make the whisper model cloneable (#1200)	Laurent Mazare	2023-10-27	2	-1/+11
*	Move the common quantized-nn code to a shared module. (#1063)	Laurent Mazare	2023-10-09	1	-42/+6
*	Better control on the optional dequantization in QMatMul (#1049)	Laurent Mazare	2023-10-07	1	-6/+5
*	Add a quantized variant of whisper (#1017)	Laurent Mazare	2023-10-02	3	-18/+424
*	Use softmax-last-dim in whisper. (#810)	Laurent Mazare	2023-09-11	1	-2/+2
*	Move some models to candle-transformers so that it's easier to re-use. (#794)	Laurent Mazare	2023-09-10	3	-0/+652