362 commits

This branch

This branch

All branches

Author	SHA1	Message	Date
Fireblade	0b5ec320c7	streaming word level time stamps	2025-02-14 13:37:42 -05:00
David Li	2b9933479a	Disable --reload on unicorn/fastapi to avoid pegging a CPU core ... Signed-off-by: David Li <jiawei.davidli@gmail.com>	2025-02-13 20:12:53 -08:00
remsky	b00c9ec28d	Update README.md	2025-02-13 20:38:45 -07:00
Fireblade	4027768920	Started work on allowing streaming word level timestamps as well as transitioning the dev code so it uses a lot more from the open ai endpoint	2025-02-13 18:00:03 -05:00
Fireblade	7772dbc2e4	fixed no stream file writing	2025-02-13 16:12:51 -05:00
remsky	f587309d8f	Update README.md	2025-02-13 03:12:45 -07:00
remsky	97f82c0685	Update README.md	2025-02-13 03:11:11 -07:00
remsky	cfae7db7fc	fix: bump up audio quality settings in StreamingAudioWriter	2025-02-13 00:22:14 -07:00
remsky	37ea01eaf9	fix: download_format option for audio response, handling in create_speech	2025-02-13 00:04:21 -07:00
remsky	127aae4fab	Merge pull request #156 from eltociear/patch-1 ... docs: update README.md	2025-02-12 23:46:05 -07:00
remsky	af654d59aa	Merge pull request #155 from Krurst/master ... Update openai_compatible.py to fix lang_code	2025-02-12 23:32:24 -07:00
remsky	f585185404	Update openai_compatible.py	2025-02-12 23:31:47 -07:00
remsky	694b7435f1	Merge branch 'master' into master	2025-02-12 23:31:13 -07:00
remsky	728e18b613	Merge pull request #152 from fireblade2534/fixedstuff ... fixed a bunch of stuff	2025-02-12 23:21:12 -07:00
Fireblade	dbf2b99026	Simplifed generate_audio in tts_service mostly working (audio conversion does not work)	2025-02-12 22:42:41 -05:00
Fireblade	5b20602b8e	More work on timestamps (Does not maintain accuracy over multiple chunks)	2025-02-12 21:36:35 -05:00
Fireblade2534	6985f6ef99	more work on streaming timestamps (not working weird error) :(	2025-02-12 20:34:55 +00:00
Fireblade2534	91d370d97f	More working on streaming timestamps	2025-02-12 17:13:56 +00:00
Fireblade2534	51b6b01589	Fixed not returning enough values	2025-02-12 15:06:11 +00:00
Fireblade	5cc9d140fe	WIP	2025-02-11 22:36:19 -05:00
Fireblade	45cdb607e6	WIP	2025-02-11 22:32:10 -05:00
Fireblade	da1e280805	fix tests	2025-02-11 21:30:41 -05:00
remsky	aae90b6d2e	Merge pull request #162 from zucher/master	2025-02-11 17:32:16 -07:00
Fireblade	7cb5957848	added optional pluralization normalization	2025-02-11 19:24:29 -05:00
Fireblade	09de389b29	Added normilization options	2025-02-11 19:09:35 -05:00
Fireblade	8ea8e68b61	Fixed espeak backend erroring while initilizating causing espeak fallback to silently fail	2025-02-11 18:08:36 -05:00
Fireblade2534	84f3b8b4cb	Merge branch 'remsky:master' into fixedstuff	2025-02-11 17:04:20 -05:00
zucher	1e14fd8724	Fix chart ingress issue	2025-02-11 21:02:58 +00:00
remsky	7d4ded6e2e	Merge pull request #157 from zucher/master ... Add Helm chart	2025-02-11 12:08:59 -07:00
Vincent Bailleau	d4f248b3a2	Add Helm chart	2025-02-11 19:10:01 +01:00
Ikko Eltociear Ashimine	b6dd9f326b	docs: update README.md ... accomodate -> accommodate	2025-02-12 02:11:08 +09:00
Krurst	1cf011b2eb	Update openai_compatible.py to fix lang_code ... properly sets lang_code from api request, and applies config default if not set	2025-02-11 23:35:51 +08:00
Fireblade2534	64980b5bc8	made it so bytes vs bits are translated correctly	2025-02-11 15:18:10 +00:00
Fireblade2534	68cb097d9b	Merged from orgin/master	2025-02-11 14:05:14 +00:00
remsky	24b31ccbb5	-Fixed espeak engagement on gpu ... -Add default voice code setting and update language code resolution logic	2025-02-11 04:49:48 -07:00
Fireblade	737e49a3f9	removed testing start-gpu.bat	2025-02-10 21:49:05 -05:00
Fireblade	ab1c21130e	Made the api use the normalizer, fixed the wrong version of espeak, added better normilzation, improved the sentence splitting, fixed some formatting	2025-02-10 21:45:52 -05:00
remsky	9b76ce2071	Create LICENSE	2025-02-10 02:08:51 -07:00
remsky	3f45a506de	Update README.md	2025-02-10 02:04:50 -07:00
remsky	09b7c2cf1e	Update README badges and add script to automate badge updates	2025-02-09 23:01:53 -07:00
remsky	cc4d5ac3c2	Acknowledging @rvuyyuru2 work on weighted voices from PR #92 (Implemented a bit differently)	2025-02-09 22:32:02 -07:00
remsky	1651c43c85	Merge branch 'master' of https://github.com/remsky/Kokoro-FastAPI	2025-02-09 20:57:04 -07:00
remsky	8ed2f2afb6	Add model listing and retrieval endpoints with tests	2025-02-09 20:55:21 -07:00
remsky	d73ed87987	Update handling in generate_captioned_speech to stream immediately, templink for caption file, and add unit tests for captioned speech generation	2025-02-09 20:26:59 -07:00
remsky	a91e0fe9df	Ruff check + formatting	2025-02-09 18:32:17 -07:00
remsky	89a6021023	Update README.md	2025-02-09 15:35:35 -07:00
remsky	53512b3d5e	Merge branch 'master' of https://github.com/remsky/Kokoro-FastAPI	2025-02-08 20:36:56 -07:00
remsky	af0e6dad6e	espeak-loader broken link fix, invalid pipeline state	2025-02-08 20:36:50 -07:00
remsky	a1e3ac1351	Update README.md	2025-02-08 01:51:41 -07:00
remsky	2a37905221	Update README.md	2025-02-08 01:49:06 -07:00