public-mirrors/Kokoro-FastAPI
1
0
Fork 0
mirror of https://github.com/remsky/Kokoro-FastAPI.git synced 2025-08-05 16:48:53 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
366 commits 9 branches 14 tags 72 MiB
Commit graph

366 commits

This branch
This branch
All branches
Author SHA1 Message Date
Fireblade2534
9f67366278
Merge branch 'master' into master 2025-03-11 11:06:33 -04:00
CodePothunter
d2b93e8da1 Fix speed parameter support for TTS generation 
- Update InstancePool to accept and process speed parameter
- Modify TTSService to pass speed to instance pool
- Update Test.py with new port and authentication
- Adjust start-gpu.sh to use port 50888
 2025-03-11 20:49:41 +08:00
Fireblade2534
dafc87ddef
Merge pull request #199 from blakkd/master
Some checks failed
CI / test (3.10) (push) Has been cancelled
Details 
converted CRLF ending lines to LF ones in api/src/structures/custom_responses.py
 2025-03-10 18:14:29 -04:00
Fireblade2534
6edc44edf3
Update docker-compose.yml 2025-03-10 18:12:52 -04:00
Fireblade2534
4d0f72b84e
Merge pull request #232 from FotieMConstant/patch-1 
docs: added a note for Apple Silicon users regarding GPU build
 2025-03-10 18:05:35 -04:00
CodePothunter
e67264f789 Fix BUGs of streaming non-wav format audio; improve robustness of releasing audio container 
Refactor StreamingAudioWriter to improve audio encoding reliability

- Restructure audio encoding logic for better error handling
- Create a new method `_create_container()` to manage container creation
- Improve handling of different audio formats and encoding scenarios
- Add error logging for audio chunk encoding failures
- Simplify container and stream management in write_chunk method
 2025-03-10 13:26:55 +08:00
fotiecodes
c3d1f0f45a
docs: added note for Apple Silicon users regarding GPU build 
Clarified in the Docker documentation that the GPU build is CUDA-only and not supported on Apple Silicon (M1/M2/M3) to avoid confusion. Advised using the CPU build (docker/cpu) and noted that MPS support is still to come.
 2025-03-10 00:20:42 +03:00
Fireblade
fbdedfb131 Combine the language code checks 2025-03-09 15:16:45 -04:00
CodePothunter
f998cf8d01 Fix bugs of generating empty file when using streaming mode. 
The reason is that when stream=True, the audio conversion functions are not really called.
 2025-03-09 14:12:18 +08:00
Fireblade
3e6ee65482 Simple fixes and translations 2025-03-08 22:48:52 -05:00
CodePothunter
70c0d506de Add start-gpu.sh script for GPU-enabled FastAPI deployment 
- Create GPU-specific startup script
- Set environment variables for GPU and project configuration
- Use uv to install GPU extras and run FastAPI server
 2025-03-07 20:24:07 +08:00
CodePothunter
6e79b252d0 Merge branch 'master' of https://github.com/CodePothunter/Kokoro-FastAPI 2025-03-07 20:20:18 +08:00
CodePothunter
2dc9b81ad5 Fix audio chunk concatenation and dtype conversion confliction 
- Modify audio chunk concatenation to handle float32 audio data
- Add explicit conversion from float32 to int16 using amplitude scaling
- Remove unnecessary dtype specification in np.concatenate
 2025-03-07 20:17:35 +08:00
CodePothunter
8fe85c3386
Delete start-gpu.sh 2025-03-07 15:20:04 +08:00
CodePothunter
5c8f941f06 Add API authentication and configuration improvements 
- Implement OpenAI-compatible API key authentication
- Add configuration options for GPU instances, concurrency, and request handling
- Update README with authentication instructions
- Modify configuration and routing to support optional API key verification
- Enhance system information and debug endpoints to expose authentication status
 2025-03-07 11:36:13 +08:00
Fireblade2534
a578d22084
Merge pull request #221 from Chuui9739/fix-MediaSource-error
Some checks failed
CI / test (3.10) (push) Has been cancelled
Details 
Repair the error 'Error: Error generating speech: Failed to execute '…
 2025-03-06 17:52:21 -05:00
Chuui9739
d69a4c3b6e
Update AudioService.js 
Change tab to space
 2025-03-05 17:30:11 +08:00
Anthony
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.' 2025-03-05 17:04:53 +08:00
Fireblade2534
d67570ab21
Merge pull request #210 from fireblade2534/preserve-custom-phenomes 
This fix allows for inputing custom pronuncations through text. For example: "This is a test of a [bla bla](/ðɪs ɪz ˈoʊnli ɐ tˈɛst/) system." It ensures that normalization does not affect custom prnouncations
 2025-03-02 14:37:07 -05:00
Fireblade2534
43576c4a76
Remove random 1 2025-03-01 12:45:41 -05:00
Fireblade2534
2a54140c46
Merge pull request #211 from fireblade2534/master
Some checks failed
CI / test (3.10) (push) Has been cancelled
Details 
fixes the low quality fix not working properly
 2025-02-28 22:01:00 -05:00
Fireblade
226a75e782 fixes the low quality fix not working properly 2025-02-28 21:57:33 -05:00
Fireblade
f415ce7109 don't replace brackets as that is handled in misaki 2025-02-28 21:39:12 -05:00
Fireblade
906cf77a65 preserve custom phenomes 2025-02-28 21:37:46 -05:00
remsky
9c6e72943c
Merge pull request #207 from fireblade2534/master
Some checks failed
CI / test (3.10) (push) Has been cancelled
Details 
Fix low quality because audio was being encoded at a lower bitrate
 2025-02-27 03:43:38 -07:00
Fireblade
9247bc3a12 notremoved the rate argument which apperently means bitrate 2025-02-26 21:51:00 -05:00
Fireblade
980bc5b4a8 Fix low quality because audio was being encoded at a lower bitrate 2025-02-26 20:52:38 -05:00
blakkd
664451e11c added docker to video group 2025-02-24 02:16:07 +01:00
blakkd
3c5029f801 converted CRLF ending lines to LF ones in api/src/structures/custom_responses.py 
let ruff organise the imports
 2025-02-24 02:11:48 +01:00
remsky
7d73c3c7ee
Merge pull request #173 from fireblade2534/streaming-word-timestamps
Some checks failed
CI / test (3.10) (push) Has been cancelled
Details 
Streaming word timestamps
 2025-02-22 23:12:22 -07:00
Fireblade
e6feea78a3 Testing error 2025-02-22 15:29:26 -05:00
Fireblade
5de3cace3b Fix some tests and allow running the docker container offline 2025-02-22 15:17:28 -05:00
Fireblade
c1207f085b Merge remote-tracking branch 'upstream/master' into streaming-word-timestamps 2025-02-22 14:58:28 -05:00
remsky
39cc056fe2
Merge pull request #179 from fireblade2534/normalization-changes
Some checks failed
CI / test (3.10) (push) Has been cancelled
Details
2025-02-21 20:00:15 -07:00
remsky
3fd37b837b
Merge pull request #186 from fireblade2534/Add-.gitattribues-file 2025-02-21 19:59:53 -07:00
remsky
a6defbff18
Merge pull request #171 from randombk/pr-no-reload 2025-02-21 19:59:21 -07:00
Fireblade
c5a3e13670 Converted the stream writer to use pyav 2025-02-19 23:10:51 -05:00
Fireblade
4ee4d36822 Fixes a couple of issues with audio triming and prevents errors with single voice weights 2025-02-18 18:12:49 -05:00
Fireblade
7f15ba8fed Add a .gitattributes 2025-02-18 17:44:03 -05:00
Fireblade
f2b2f41412 fixed wrong varible name bug 2025-02-16 17:07:41 -05:00
Fireblade
cb22aab239 Fix streaming a wav file with captions not reaturning any captions (This is only a problem because wav streaming does not acually work) 2025-02-16 16:49:33 -05:00
Fireblade
e3dc959775 Simplify code so erverything uses AudioChunks 2025-02-16 15:37:01 -05:00
Fireblade
9c0e328318 made it skip text normalization when using other languages as it only supports english 2025-02-16 14:16:18 -05:00
Fireblade
41598eb3c5 better parsing for times and phone numbers 2025-02-15 19:02:57 -05:00
Fireblade
3290bada2e changes to how money and numbers are handled 2025-02-15 17:48:12 -05:00
Fireblade
4802128943 Replaced default voice with af_heart as af doesn't exist 2025-02-15 12:36:36 -05:00
Fireblade
8c457c3292 fixed final test 2025-02-15 09:49:15 -05:00
Fireblade
1a6e7abac3 fixed a bunch of tests 2025-02-15 09:40:01 -05:00
Fireblade
1a03ac7464 Fixed some tests 2025-02-14 15:00:47 -05:00
Fireblade
353fe79690 fix small error 2025-02-14 14:39:24 -05:00