10 Commits (d71e567656f2cd373235e262dc97b811ca64afdf)

Author	SHA1	Message	Date
Georgi Gerganov	d71e567656	Update README.md	2 years ago
Georgi Gerganov	62897e8ae6	Update README.md	2 years ago
Georgi Gerganov	3bcdbdfc32	Reduce memory usage even more + better sampling ... - The encode/decode memory buffers are now reused - If the 30-sec segment goes for too long without a timestamp token, we force one. Improves transcription for large model - Stereo support - Add "micro-machines.wav" sample	2 years ago
Georgi Gerganov	310f4883d1	Update README.md	2 years ago
Georgi Gerganov	fd3f3d748f	Update README.md	2 years ago
Georgi Gerganov	5877c3578e	ref #4 : added transcription timestamps ... Can be turned off with "-nt" argument. Performance has also improved.	2 years ago
Georgi Gerganov	4352a6018b	Update README.md	2 years ago
Georgi Gerganov	f888c2373d	Flash + language support (ref #2) ... - Achieved big performance improvement + memory usage reduction - Can now translate / transcribe different languages	2 years ago
Georgi Gerganov	476182e439	Update README.md and simplify usage	2 years ago
Georgi Gerganov	f2456f8d93	Create README.md	2 years ago