Commit graph

34 commits

Author SHA1 Message Date
Fireblade
c1207f085b Merge remote-tracking branch 'upstream/master' into streaming-word-timestamps 2025-02-22 14:58:28 -05:00
Fireblade
7f15ba8fed Add a .gitattributes 2025-02-18 17:44:03 -05:00
Fireblade
e3dc959775 Simplify code so erverything uses AudioChunks 2025-02-16 15:37:01 -05:00
Fireblade
34acb17682 Mostly completed work on refractoring a bunch of code as well as streaming word level time stamps 2025-02-14 14:29:47 -05:00
Fireblade
0b5ec320c7 streaming word level time stamps 2025-02-14 13:37:42 -05:00
Fireblade
7772dbc2e4 fixed no stream file writing 2025-02-13 16:12:51 -05:00
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
51b6b01589 Fixed not returning enough values 2025-02-12 15:06:11 +00:00
Fireblade
45cdb607e6 WIP 2025-02-11 22:32:10 -05:00
Fireblade2534
68cb097d9b Merged from orgin/master 2025-02-11 14:05:14 +00:00
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
a91e0fe9df Ruff check + formatting 2025-02-09 18:32:17 -07:00
remsky
a0dc870f4a -fix voice selection not matching language phonemes
-added voice language override parameter
2025-02-08 01:29:15 -07:00
Fireblade2534
90f168f63d fixed some problems in the build system and model download system 2025-02-07 18:30:59 +00:00
remsky
fe6c9acaf5 Update Docker configuration, enhance audio service autoplay, and improve styling 2025-02-05 02:45:28 -07:00
remsky
6c234a3b67 Update dependencies, enhance voice management, and add captioned speech support 2025-02-04 19:41:41 -07:00
remsky
4c90a89545 Initial commit of Kokoro V1.0-only integration 2025-02-04 03:37:56 -07:00
remsky
903bf91c81 v1_0 multilanguage initial support
-note: all languages currently installed, selected by prefix of first chosen voice in call
2025-02-03 03:33:12 -07:00
remsky
2dfad62b5b Update .gitignore and benchmark scripts for GPU support; enhance TTS service handling and session management 2025-01-30 05:47:28 -07:00
remsky
f61f79981d -Add debug endpoint for system stats
-Adjust headers, generate from phonemes, etc
2025-01-30 04:44:04 -07:00
remsky
9867fc398f WIP: v1_0_0 migration 2025-01-28 13:52:57 -07:00
remsky
00497f8872 Refactor: Consolidate PyTorch CPU and GPU backends into a single PyTorchBackend class; remove obsolete files 2025-01-25 13:33:42 -07:00
remsky
9efb9db4d9 Fix: VoiceManager singleton instantiation 2025-01-24 05:30:56 -07:00
remsky
20658f9759 Performance: Adjust session timeout and GPU memory limit; minim voice pre-caching and improve singleton instance management 2025-01-24 05:01:38 -07:00
remsky
8eb3525382 Refactor configuration and enhance web interface: update GPU settings, add speed control, and improve input handling for audio generation 2025-01-23 04:54:55 -07:00
remsky
8e8f120a3e Update configuration to disable local voice saving, enhance voice validation logic, and remove deprecated test file 2025-01-23 02:00:46 -07:00
remsky
df4cc5b4b2 -Adjust testing framework for new model
-Add web player support: include static file serving and HTML interface for TTS
2025-01-22 21:11:47 -07:00
remsky
66f46e82f9 Refactor ONNX GPU backend and phoneme generation: improve token handling, add chunk processing for audio generation, and initial introduce stitch options for audio chunks. 2025-01-22 17:43:38 -07:00
remsky
d50214d3be Enable ONNX GPU support in Docker configurations and refactor model file handling 2025-01-22 05:00:38 -07:00
remsky
4a24be1605 Refactor model loading and configuration: update, adjust model loading device,. add async streaming examples and remove unused warmup service. 2025-01-22 02:33:29 -07:00
remsky
21bf810f97 Enhance model inference: update documentation, add model download scripts for PyTorch and ONNX, and refactor configuration handling 2025-01-21 21:44:21 -07:00
remsky
ab28a62e86 Refactor inference architecture: remove legacy TTS model, add ONNX and PyTorch backends, and introduce model configuration schemas 2025-01-20 22:42:29 -07:00