public-mirrors/Kokoro-FastAPI
1
0
Fork 0
mirror of https://github.com/remsky/Kokoro-FastAPI.git synced 2025-04-13 09:39:17 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Commit graph

  • bab01f8f2c
         Merge 116911c8ba into f1fa340494 fondoger 2025-04-12 14:31:58 +00:00
  • 116911c8ba Fix unit tests fondoger 2025-04-12 22:31:53 +08:00
  • 655c243f1d Fix bug: same reference issue fondoger 2025-04-12 22:08:05 +08:00
  • 50fba72169
         Merge 3e23fb0cf0 into f1fa340494 Lukin 2025-04-08 04:00:35 +00:00
  • 3e23fb0cf0 Refactor smart_split function to enhance handling of custom phonemes and normalization. Improved logging for clarity and error handling, ensuring compatibility with both ID and original tag formats. Streamlined text processing logic for better performance and maintainability. Lukin 2025-04-08 12:00:27 +08:00
  • e42f7fcb67 Refactor get_sentence_info function to improve sentence processing and phoneme restoration. Enhanced regex for sentence splitting, added detailed docstring for clarity, and improved handling of trailing newlines and whitespace-only sentences. Updated tokenization logic to ensure robust error handling during processing. Lukin 2025-04-08 11:52:15 +08:00
  • 0d1dd666f2 Refactor TTS service to simplify language code determination and improve logging. Removed unnecessary comments and streamlined voice path handling for clarity. Lukin 2025-04-08 11:40:51 +08:00
  • 66201494d0 Refactor TTS service to improve voice combination logic and error handling. Updated voice parsing to support combined voices with weights, enhanced normalization handling, and streamlined audio generation process. Improved logging for better debugging and removed unnecessary comments for clarity. Lukin 2025-04-08 11:38:07 +08:00
  • 7a838ab3e8 Refactor TTS service to improve audio chunk handling and filename safety. Removed unnecessary comments, adjusted text processing for legacy backends, and enhanced error handling during audio stream generation. Updated filename regex to restrict allowed characters for safer filenames. Lukin 2025-04-08 11:17:46 +08:00
  • 88b9349198 Enhance StreamingAudioWriter to support MP3 encoding without Xing VBR header and conditionally set bit rate for applicable formats. Improved error handling by using self.format in exceptions. Lukin 2025-04-08 10:21:43 +08:00
  • 207d709de1 Refactor TTS service to improve filename safety and audio chunk handling. Updated filename regex to allow additional characters, enhanced silence chunk creation for AudioService, and ensured final audio output is consistently in int16 format. Removed premature writer closure in the finalization process, delegating responsibility to the caller. Lukin 2025-04-08 09:38:59 +08:00
  • 5dbf2e2e4b
         Merge branch 'master' into fondoger/silence-tags Fireblade2534 2025-04-07 14:20:29 -04:00
  • 4b334beff4 Enhance test coverage for text processing and TTS service. Updated assertions in test_get_sentence_info_phenomoes to verify placeholder presence and token counts. Modified smart_split tests to unpack additional values and ensure proper handling of text and tokens. Improved clarity in test assertions for punctuation preservation. Lukin 2025-04-08 00:47:12 +08:00
  • c0da571857 Refactor TTS service and text processing to enhance handling of pauses, newlines, and custom phonemes. Updated smart_split to manage pause tags and improved error logging. Adjusted audio generation logic for better performance and clarity. Lukin 2025-04-07 14:12:18 +08:00
  • b31f79d8d7 Enhance TTS service to handle pauses and trailing newlines in text processing. Updated smart_split to preserve newlines and added logic for generating silence chunks during pauses. Improved error handling and logging for audio processing. Lukin 2025-04-07 13:21:49 +08:00
  • f8e573ce69
         Merge b4ba360084 into f1fa340494 Jerry.Wang 2025-04-06 05:17:56 -07:00
  • b19fd1d179 Fix merge conflicts Kishor Prins 2025-04-05 08:33:21 -07:00
  • f1fa340494
         Update README.md master remsky 2025-04-05 04:09:28 -06:00
  • 253855e6b9
         Merge pull request #278 from remsky/master release remsky 2025-04-04 22:09:27 -06:00
  • d826de87ed Minor change to trigger new release remsky 2025-04-04 22:07:26 -06:00
  • 59be119cc4
         Merge pull request #276 from remsky/maintenance/automations remsky 2025-04-04 21:19:09 -06:00
  • 10f240daad Add tag existence check in release workflow remsky 2025-04-04 19:38:27 -06:00
  • 10caafe3fb Adjust CONTRIBUTING.md, readme docker information and notes remsky 2025-04-04 19:30:13 -06:00
  • ba796ef003 Update CHANGELOG.md for version 0.3.0: add new features, changes, fixes, and removals remsky 2025-04-04 18:53:13 -06:00
  • a28de9bc66
         Delete readme-parts/config.yaml remsky 2025-04-04 17:28:06 -06:00
  • d004b6d304
         Apply suggestions from copilot Fireblade2534 2025-04-04 19:06:59 -04:00
  • 7f0e06ea6b
         Update normalizer.py Fireblade2534 2025-04-04 19:06:13 -04:00
  • afa879546c CONTRIBUTING + Ruff format remsky 2025-04-04 16:58:07 -06:00
  • 447f9d360c Ruff check remsky 2025-04-04 16:50:46 -06:00
  • 6a2d3a54cf Bump version to 0.3.0 and update related configurations; add misaki patch script and remove obsolete build workflow remsky 2025-04-04 16:49:10 -06:00
  • a1e686cccb Fix bug: wrong order or custom phoneme fondoger 2025-04-04 23:25:24 +08:00
  • 8c08655a08 Change silent tag syntax to [silent 1.5s] fondoger 2025-04-04 03:49:27 +08:00
  • 1d163f84f9 Update readme fondoger 2025-04-04 03:16:40 +08:00
  • 2e2b3e9e0e Feature: Support silence tags. eg:[silent](0.5s) fondoger 2025-04-04 02:50:41 +08:00
  • 398060fde3
         Merge 4b7f4829a2 into e2313abe72 fondoger 2025-04-03 14:39:07 +08:00
  • e2313abe72
         Merge pull request #266 from rampadc/master remsky 2025-04-02 22:04:04 -06:00
  • 94e53055d4 Remove casual_conv1d Kishor Prins 2025-04-01 13:19:59 -07:00
  • 5067a47ff9 wip: fix mp3 Cong Nguyen 2025-04-01 18:05:37 +11:00
  • 9e595d9ad5 Revert to upstream Kokoro Kishor Prins 2025-03-31 14:02:32 -07:00
  • 19ac239aeb Add notes about performance inside docker compose Kishor Prins 2025-03-31 14:01:29 -07:00
  • 4b7f4829a2 Fix decimal Fireblade2534 2025-03-31 13:33:18 +00:00
  • cacdfe7947 Added .co as a valid domain Fireblade2534 2025-03-31 13:30:25 +00:00
  • fd86395e98 Reverted the kokoro version bump and change the phenomizer to use the phenomizer that the rest of the text uses. Fireblade2534 2025-03-31 13:28:44 +00:00
  • 64ced408b7 removed duplicated env and align with other shell scripts Cong Nguyen 2025-03-31 03:54:41 +11:00
  • c7f09bf467 Upgrade kokoro/misaki version fondoger 2025-03-30 22:18:57 +08:00
  • 88f19d7751 Improve text normalize to keep original timestamps fondoger 2025-03-30 21:31:17 +08:00
  • e9d9921612
         Merge branch 'remsky:master' into master Kishor Prins 2025-03-29 19:15:01 -07:00
  • 65f6b979c3 Enhance temp file handling with error tracking and update Docker Compose to run as non-root user remsky 2025-03-29 17:01:15 -06:00
  • 2185b1b17d
         Merge branch 'remsky:master' into master Kishor Prins 2025-03-27 13:10:12 -07:00
  • d0c13f6401
         Merge pull request #257 from richardr1126/update-helm-charts Fireblade2534 2025-03-26 10:11:52 -04:00
  • 3db522b742 Merge branch 'master' of github.com:kprinssu/Kokoro-FastAPI Kishor Prins 2025-03-25 15:42:21 -07:00
  • 4f149abb39 Use my fork of Kokoro Kishor Prins 2025-03-25 15:42:05 -07:00
  • fe99bb7697
         Merge pull request #256 from fireblade2534/Fixing-number-normalization remsky 2025-03-23 23:57:21 -06:00
  • a665cfc406
         Merge branch 'remsky:master' into master Kishor Prins 2025-03-23 17:13:17 -07:00
  • 3c8e1b9143 Add example folder values files for Azure AKS and Nvidia GPU Operator Richard Roberson 2025-03-22 05:54:58 -06:00
  • 14bd6a8118 Fix Helm charts health check, ingress, and values Richard Roberson 2025-03-21 22:05:25 -06:00
  • aba262844c Update Dockerfile to build against newer code Kishor Prins 2025-03-21 19:24:56 -07:00
  • d712308f98 Fixes relating to parsing money and tests. Also readme stuff Fireblade2534 2025-03-21 18:03:09 +00:00
  • 8d73c90224
         Merge pull request #253 from fireblade2534/segfault-fixes remsky 2025-03-21 02:49:29 -06:00
  • c24aeefbb2 Aculy fixed tests this time Fireblade2534 2025-03-20 19:15:07 +00:00
  • c902b2ca0d probably fix tests Fireblade2534 2025-03-20 16:27:18 +00:00
  • 8f23bf53a4 Inital test commit of segfault fixes Fireblade2534 2025-03-20 16:20:28 +00:00
  • 1d017554fe Fix merge conflicts Kishor Prins 2025-03-19 19:28:05 -07:00
  • 0d7570ab50
         Merge pull request #240 from fireblade2534/fixes remsky 2025-03-18 04:27:17 -06:00
  • 1184bc70e8
         Merge pull request #244 from mpnsk/fix-siriwave-path remsky 2025-03-18 04:23:25 -06:00
  • 04b5dfa84c
         Merge pull request #233 from rampadc/master remsky 2025-03-18 04:21:49 -06:00
  • 19fdff3431
         Merge 6e617ed5f3 into 9091be8c3e chai51 2025-03-16 20:47:27 +08:00
  • 9091be8c3e
         Merge pull request #241 from kimnzl/master Fireblade2534 2025-03-15 16:35:53 -04:00
  • 22185dbc89 Fixed the ps1 files downloading packages before the venv and made all starrt scripts auto download models Fireblade 2025-03-15 16:35:06 -04:00
  • 2f420daad5 use local js file instead of the unpkg cdn mpnsk 2025-03-15 16:36:03 +01:00
  • 0735999c59 Add Windows powershell scripts Kim 2025-03-15 02:19:25 +13:00
  • 9f9e9b601e Fixes not returning a download link if streaming is off and return_download_link is true Fireblade 2025-03-13 16:23:49 -04:00
  • 6e617ed5f3 fix Chinese and English mixing chai 2025-03-13 15:07:35 +08:00
  • acb7d05515
         Merge branch 'master' into master Fireblade2534 2025-03-12 11:17:44 -04:00
  • e4744f5545
         Merge pull request #235 from fireblade2534/fixes remsky 2025-03-12 02:22:04 -06:00
  • aa403f2070 Adds the ability to subtract voices Fireblade 2025-03-11 14:28:48 -04:00
  • 939be30ccc
         Merge 9f67366278 into dafc87ddef CodePothunter 2025-03-11 15:06:35 +00:00
  • 9f67366278
         Merge branch 'master' into master Fireblade2534 2025-03-11 11:06:33 -04:00
  • d2b93e8da1 Fix speed parameter support for TTS generation CodePothunter 2025-03-11 20:49:41 +08:00
  • dafc87ddef
         Merge pull request #199 from blakkd/master Fireblade2534 2025-03-10 18:14:29 -04:00
  • 6edc44edf3
         Update docker-compose.yml Fireblade2534 2025-03-10 18:12:52 -04:00
  • 4d0f72b84e
         Merge pull request #232 from FotieMConstant/patch-1 Fireblade2534 2025-03-10 18:05:35 -04:00
  • e67264f789 Fix BUGs of streaming non-wav format audio; improve robustness of releasing audio container CodePothunter 2025-03-10 13:26:55 +08:00
  • 6d2ca6421e change back port to 8880 Cong Nguyen 2025-03-10 11:59:19 +11:00
  • 9a9bc4aca9 added support for mps on mac with apple silicon Cong Nguyen 2025-03-10 11:58:45 +11:00
  • c3d1f0f45a
         docs: added note for Apple Silicon users regarding GPU build fotiecodes 2025-03-10 00:20:42 +03:00
  • fbdedfb131 Combine the language code checks Fireblade 2025-03-09 15:16:45 -04:00
  • f998cf8d01 Fix bugs of generating empty file when using streaming mode. CodePothunter 2025-03-09 14:12:18 +08:00
  • 3e6ee65482 Simple fixes and translations Fireblade 2025-03-08 22:48:52 -05:00
  • 70c0d506de Add start-gpu.sh script for GPU-enabled FastAPI deployment CodePothunter 2025-03-07 20:24:07 +08:00
  • 6e79b252d0 Merge branch 'master' of https://github.com/CodePothunter/Kokoro-FastAPI CodePothunter 2025-03-07 20:20:18 +08:00
  • 2dc9b81ad5 Fix audio chunk concatenation and dtype conversion confliction CodePothunter 2025-03-07 20:17:35 +08:00
  • 8fe85c3386
         Delete start-gpu.sh CodePothunter 2025-03-07 15:20:04 +08:00
  • 5c8f941f06 Add API authentication and configuration improvements CodePothunter 2025-03-07 11:36:13 +08:00
  • a578d22084
         Merge pull request #221 from Chuui9739/fix-MediaSource-error v0.2.3 Fireblade2534 2025-03-06 17:52:21 -05:00
  • d69a4c3b6e
         Update AudioService.js Chuui9739 2025-03-05 17:30:11 +08:00
  • f4970a92f4 Repair the error 'Error: Error generating speech: Failed to execute 'endOfStream' on 'MediaSource': The 'updating' attribute is true on one or more of this MediaSource's SourceBuffers.' Anthony 2025-03-05 17:04:53 +08:00
  • b4ba360084 added basic authentication, to enable it, set HTTP_USERNAME and HTTP_PASSWORD in environment variables Jerry.Wang 2025-03-04 14:14:04 +08:00
  • f2c5bc1b71
         Merge branch 'remsky:master' into fixes Fireblade2534 2025-03-02 21:39:17 -05:00
  • b3d5f4de08 fixes and corrections to code that didn't cause errors but didn't really make sense Fireblade 2025-03-02 21:36:34 -05:00