4090ff2665
chore(format): run black on dev ( #915 )
...
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2025-03-14 12:34:46 +09:00
d582fd5d70
feat(example): add new API ( #913 )
...
Add FastAPI-based OpenAI-compatible Text-to-Speech API and Audio Format Conversion Tools
2025-03-14 12:32:50 +09:00
d21106f9e4
chore(format): run black on dev ( #827 )
...
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-12-04 01:18:54 +09:00
00c56ee6af
fix(tools): load audio close file after reading
2024-11-28 22:37:41 +09:00
c3948c8674
feat(tools): load_audio supports mean of stereo
2024-11-28 01:18:12 +09:00
b9b007ef7f
feat(core): dvae&vocos switch to safetensors
2024-10-16 01:21:09 +09:00
8e6e6c97f7
fix(norm): 不能读出啊和呃的bug ( #783 )
...
Co-authored-by: dragon <com888yy@gmail.com >
Co-authored-by: 源文雨 <41315874+fumiama@users.noreply.github.com >
2024-10-15 15:07:22 +00:00
b3a180e8e2
optimize(utils): device selection & jit
2024-10-10 21:47:12 +09:00
c06f1d45bf
feat(dl): support new safetensors model & drop gitcode 👎
2024-08-28 22:45:57 +08:00
f3dcd970c9
optimize: separate speaker from tokenizer
...
- move `spk_stat.pt` into config
- move `sample_audio_speaker` to DVAE
- update rvcmd to `v0.2.7`
2024-08-06 17:35:41 +08:00
80b24e66b7
fix(tokenizer): weights_only warning by dropping .pt
2024-08-05 21:06:52 +08:00
528a1fe075
doc: update roadmap
2024-07-19 01:32:07 +09:00
2d293cafd1
chore(format): run black on dev ( #591 )
...
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-07-19 01:23:51 +09:00
b4da2375ea
feat(algorithm): impl. zero shot demo
2024-07-19 01:23:02 +09:00
9f0b7a048d
feat(dvae): add encoder
2024-07-18 18:31:40 +09:00
d4cc9bb9dc
fix(checksum): json ending
2024-07-16 17:23:46 +09:00
27331c3399
feat(config): drop download of folder config
2024-07-16 17:10:49 +09:00
d089bd2492
chore(format): run black on dev ( #560 )
...
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-07-10 16:53:29 +09:00
af8a4e378c
chore(tools): rename wav_arr_to_mp3_view to pcm_arr_to_mp3_view
2024-07-10 16:50:14 +09:00
580463ce22
fix(test): int16 rms overflow
2024-07-10 15:39:49 +09:00
e049abab96
chore(test): update test according to #521
2024-07-10 15:06:59 +09:00
c7ce7c5975
chore(format): run black on dev ( #554 )
...
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-07-09 22:07:41 +09:00
fb4676e3de
optimize(tools): drop unsafe convert
2024-07-09 21:04:36 +09:00
f1c6da98c1
chore(format): run black on dev ( #536 )
...
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-07-06 00:42:17 +09:00
a5fec6653d
fix(gpt): compile failed
2024-07-06 00:15:04 +09:00
6e7a261fa8
fix: AttributeError on py3.8
2024-07-03 16:28:35 +09:00
5b537f3a4d
chore(format): run black on main ( #494 )
...
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-06-28 21:11:09 +09:00
03364a58a7
fix(webui): fallback to wav if ffmpeg not installed ( #493 )
2024-06-28 21:10:29 +09:00
52d75d54c1
chore(format): run black on main ( #475 )
...
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-06-27 16:57:52 +09:00
cc58be254c
fix(webui): crash on non-ffmpeg env. ( #466 )
2024-06-26 17:48:43 +09:00
0744bb3418
feat(examples): use mp3 output by default ( #449 )
2024-06-25 21:41:25 +09:00
93db24b4b2
chore(format): run black on main ( #443 )
...
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-06-25 17:22:13 +09:00
8620dfbb3a
fix(load): KeyError: 'sha256_config_decoder_yaml' ( fix #438 ) ( #441 )
...
by removing environment vars
2024-06-25 17:16:30 +09:00
cae0fec15b
fix(colab): color log printing ( #430 )
2024-06-24 22:39:50 +09:00
f4121844e6
doc: sync to latest grammar ( #427 )
2024-06-24 22:11:56 +09:00
c8cb6bd327
feat: add normalizer interface & move instances out ( #420 )
2024-06-24 17:28:14 +09:00
21a216f6d2
Merge pull request #414 from aliencaocao/fix-webui-demo
...
Add init.py to tools and web to fix launching webui demo
2024-06-24 09:17:50 +09:00
5d20028316
optimize(utils): jit HomophonesReplacer
2024-06-23 22:39:11 +09:00
724f524629
Add init.py to tools and web to fix launching webui demo
2024-06-23 20:33:12 +08:00
93ef96b173
feat: apply TorchSeedContext
2024-06-23 21:22:23 +09:00
4dd1f88073
optimize: core & model
...
### all
- reduce redundant code
- add `_` to some inner calls
### core
- rename `check_model` to `has_loaded`
- new api `download_models`
- move vocos out of models dict (further target: remove the dict `pretrain_models`)
- new api `unload`
- new api `decode_to_wavs`
### model
- fix grad mul issue in dvae
- optimize progress bar display
- optimize tensor operations
2024-06-23 17:17:33 +09:00
2eb97d212f
optimize: log printing ( #411 )
2024-06-23 01:27:49 +09:00
1430c95a22
feat(ipynb): apply logger to notebook ( #410 )
2024-06-23 00:17:19 +09:00
3e0d87bca0
fix(tools): log formatting ( #401 )
...
- introduce numba
- move audio normalization functions to tools/audio
- remove IPython from tools/cmd
2024-06-22 14:59:06 +09:00
a851b9a9fe
optimize: log & webui ( #398 )
...
- move log definition out of ChatTTS
- apply colorful log level
- optimize webui logic
- split webui into 2 files for clear reading
2024-06-22 01:47:56 +09:00
a63e9c2adf
feat(core): add load_models source local ( #361 )
...
rename original `local` to `custom`
2024-06-19 18:14:29 +09:00
github-actions[bot]