- deps: Support Python 3.12, end support for Python 3.8, explicitly specify click as a dependency, update deps (#1165) (
a7ceffa)
- pre-sd: Add leading zeros for 4-digit width of the output file name's numeric part #1154 (#1155) (
41b147f)
- pre-sd: Set speaker-diarization version to 3.1 for pyannote.audio 3.1.1 compatibility (#1157) (
9bd3089)
- Add Priyanshu-hawk as a contributor for code (#1148) (
d6888db) - Add marcellocirelli as a contributor for bug (#1147) (
8795709)
- readme: Add description of repository maintenance status (#1143) (
3f537b0) - Add SamuelSwartzberg as a contributor for security (#1146) (
cddb722) - Add 4ll0w3v1l as a contributor for code (#1141) (
df699c7)
- pre-sd: Make Pyanote.audio use GPU (
c9d49ca)
- deps: Update dependency lightning to v2.1.0 (#975) (
4637f69) - deps: Update dependency transformers to v4.34.0 (#977) (
6bb2555)
- deps: Update dependency librosa to v0.10.1 (#974) (
3ae20b7) - deps: Update dependency torchcrepe to v0.0.22 (#973) (
ad7b2bf)
- readme: Add instructions for pipx installation, update torch urls (#899) (
0b02c49) - Add shenberg as a contributor for userTesting, ideas, and code (#810) (
319ddf3)
- inference: Remove weight norm on inference so metal backend will work without CPU fallback (#783) (
39ea0bc)
- cluster,preprocess_split: Add batched loading to clustering & max length per clip to split (#786) (
4179ec9)
- Add Zerui18 as a contributor for code, and ideas (#794) (
4e74fc4) - Add Ph0rk0z as a contributor for bug, and code (#793) (
8dc25c7)
- Update pretrained model url, raise error if there are no files to preprocess, shuffle files consistently (#715) (
c4c719c)
- default preset changed (
c4c719c)
- readme: Fix minor issues in README.md (#566) (
139ed18) - readme: Add notes about minimum requirements (#564) (
ae9aece)
- Add Highupech as a contributor for bug (#526) (
8eedc24) - readme: Fix typo in README.md (
1773940) - Add acekagami as a contributor for translation (#486) (
958b9fd) - readme_zh_cn: Update README_zh_CN.md (#477) (
1ccd594)
- train: Only save checkpoints on main device (
1aaaac6)
- Add sbersier as a contributor for bug (#437) (
58b936d) - Add escoolioinglesias as a contributor for video (#436) (
69f097f) - Add GarrettConway as a contributor for review (#435) (
c1e4ada) - Add BlueAmulet as a contributor for maintenance (#434) (
514ed84) - Add guranon as a contributor for bug, ideas, and code (#433) (
b9eb3fd) - Add ZeroHackz as a contributor for bug, and code (#432) (
66d5adc) - Add tybantarnusa as a contributor for bug (#431) (
e6e57b3) - Add Blacksingh as a contributor for bug (#430) (
7bc76ba) - Add escoolioinglesias as a contributor for bug, and userTesting (#429) (
f00fe6e) - Add outhipped as a contributor for bug (#428) (
7497175) - Add yxlllc as a contributor for ideas, and code (#427) (
42e35d2) - Add Lordmau5 as a contributor for ideas, maintenance, and 2 more (#426) (
352451c) - Add tonyco82 as a contributor for bug (#425) (
036ce90) - Add 75aosu as a contributor for bug (#424) (
5afc28b) - Add hxl9654 as a contributor for bug (#423) (
0953f1f) - Add DuctTapeGames as a contributor for bug (#422) (
b0f4d39) - Add Likkkez as a contributor for bug (#421) (
4a12109) - Add AlonDan as a contributor for bug (#420) (
662ec4b) - Add mmodeusher as a contributor for bug (#419) (
6a78df9) - Add Meldoner as a contributor for bug (#418) (
5586bec)
- train: Don't save model when tuning for auto batch size (
2311a35)
- train: Properly stop training after
epochshas been reached (f9bb3d8)
- train: Set persistent_workers = True in DataLoader for performance, do not save checkpoints, fix logging issue and multiple warning issues, do not do validation when global_step == 0 (#384) (
6cab9af)
- train: Allow higher segment size (#351) (
09d5a52) - cluster: Do not use weights_only in get_cluster_model() (#354) (
24c05d1)
- logger: Fix init_logger not showing debug messages in certain conditions as intended (#296) (
d3ab7d6)
- notebooks: Improves inference (#286) (
d3228df) - train: Step lr schedulers at end of epoch (#291) (
3af223e)
- Remove wrong test and trigger release (#266) (
9ea77e4) - deps: Remove pydantic constraints (#263) (
f446e3b) - Fix fastapi version to 0.88 (#261) (
a26f387) - utils: Fix get_optimal_device (#262) (
79e4b5a)
- The module structure has been completely changed, and some of the default values for configurations have also been changed. (
1a6c021)
- readme: Update allcontributors link for @MashiroSA (#210) (
650524b) - readme: Add paperspace referral (#209) (
7280012) - readme: Add paperspace link and add more description, add a link for zh-CN docs (#208) (
bc4b122)
- Add sbersier as a contributor for ideas, and userTesting (#185) (
a655bf4) - Add ColdCawfee as a contributor for bug (#177) (
87a09e6)
- gui: Fix wrong devices set as default (#176) (
6265f8f) - main: Fix -h option overridden (#175) (
52f1cfe)
- Add xieyumc as a contributor for doc (#174) (
29474d9) - readme_zh_cn: Update README_zh_CN.md (#173) (
f94a14c)
- Add nerdyrodent as a contributor for video (#168) (
78ab661) - Add heyfixit as a contributor for doc (#167) (
32a2a63) - Add Desuka-art as a contributor for bug (#165) (
fe3c6bf) - Add ruckusmattster as a contributor for bug (#163) (
2b971db) - Add pierluigizagaria as a contributor for userTesting (#160) (
6fabe8d) - Add Satisfy256 as a contributor for bug (#158) (
ee72aee) - Add DL909 as a contributor for bug (#152) (
a5e6651)
- Fix preprocessing and convert bool options to flags, use
unidecodeto decode non-ASCII filenames inpre-resample(#147) (98d7ee2)
- Preprocessing default parameters changed and some options became flags. (
98d7ee2)
- logging: Initialize logging in logger file and move version log (#131) (
441d51f) - preprocess: Fix dtype in sf.read() to save memory and fix preprocess_resample (#132) (
0af1e13) - Fix audio resampled to 22kHz (#130) (
4203f37)
- Add MashiroSA as a contributor for doc, and bug (#98) (
495b7cb) - notebook: Fix cluster inference command and improve cluster training command (#93) (
7642594)
- gui: Fix defaut for auto_play (#97) (
07920a4) - infer_tool: Fix speaker not automaticlly set to the first one if not found in cluster inference (#96) (
a643e4f)
- Add BlueAmulet as a contributor for question (#74) (
8d073e3) - Add GarrettConway as a contributor for doc (#73) (
6c6cbc6) - readme: Update README.md regarding installation, update. WSL audio support (#72) (
4f1323b)
- readme: Add links for pretrained models and fix GUI pic height (#60) (
34ac39f) - notebook: Add more explanation to notebook (#59) (
9b3c483)
- Use librosa.load() instead of soundfile.read() (#58) (
b343106) - gui: Fix window too big to show in a FHD environment (#57) (
259e6e6)
- Add ThrowawayAccount01 as a contributor for bug (#47) (
15e31fa) - Add BlueAmulet as a contributor for ideas (#46) (
a3bcb2b)
- the behaviour of preprocess_resample changes when there is a folder ./dataset_raw/44k and "44k" is no longer allowed as a speaker name in some conditions (
ac47fed)
- deps: Update dependency torch to v1.13.1 (#27) (
8826d68) - deps: Update dependency torchaudio to v0.13.1 (#28) (
989f5d9)
- Add GarrettConway as a contributor for bug (#17) (
31d9671) - notebook: Launch tensorboard (#16) (
52229ba) - Add 34j as a contributor for example, infra, and 6 more (#14) (
1b90378) - Add GarrettConway as a contributor for code (#13) (
716813f)
- main: Fix option names (
7ff34fe)
- Update notebook (
7b74606)
- notebook: Fix notebook (
3ed00cc)