piper-sample-generator

akadmin/piper-sample-generator

Fork 0

mirror of https://github.com/rhasspy/piper-sample-generator.git synced 2026-08-27 18:15:58 -04:00

Commit graph

06c9f2b56c

Merge 940b483c59 into 2971426a55 dakonu 2026-07-08 22:24:53 +02:00
940b483c59 added piper_train to pyproject.toml dakonu 2026-07-08 20:02:56 +02:00
2971426a55 Update install instructions master v3.2.0 Michael Hansen 2026-03-12 15:20:12 -05:00
275077a1a3 Include impulses Michael Hansen 2026-03-12 15:19:01 -05:00
1a8c49bd29 Move to package Michael Hansen 2026-03-12 15:16:51 -05:00
c9d824c0e2 Require sample rate in augment Michael Hansen 2026-03-12 10:48:04 -05:00
ded9350eaf Check if file Michael Hansen 2025-11-14 10:47:29 -06:00
66ec23fa49 Clean up v3.1.0 Michael Hansen 2025-09-19 16:21:32 -05:00
c0d2dd9ea4

Merge pull request #18 from kahrendt/phoneme-input Michael Hansen 2025-09-19 15:19:44 -05:00
942002d0ee

Merge branch 'master' into phoneme-input Michael Hansen 2025-09-19 15:19:31 -05:00
395aef7dbc

Merge pull request #17 from kahrendt/mps-support-v3 Michael Hansen 2025-09-19 15:09:08 -05:00
df5799c141 add support for directly inputting phonemes Kevin Ahrendt 2025-09-19 14:42:49 -04:00
af7ac7aae2 add support for MPS acceleration Kevin Ahrendt 2025-09-19 13:18:06 -04:00
5e67370ab3 Update changelog Michael Hansen 2025-08-29 15:17:12 -05:00
4d7e4b390c Update README v3.0.0 Michael Hansen 2025-08-29 15:16:20 -05:00
4057c1a620 Upgrade to torch 2, piper 1.3 Michael Hansen 2025-08-29 12:19:25 -05:00
fe411ccb2b

fix: PyTorch 2.6 compatibility in piper-sample-generator Praharsh Bhatt 2025-07-29 20:37:38 -04:00
3c8a6953fc Update .gitignore to include ONNX model files and add pt_PT-tugao-medium model configuration pedromartins 2025-05-31 19:03:53 +01:00
f98cec7dc4 Add support for ONNX models in sample generation pedromartins 2025-05-31 16:30:54 +01:00
38d02ee4d2 Adds pickle cache for audio and phonemes Evin Dunn 2024-03-04 12:25:12 -05:00
9c1019c932

Merge pull request #5 from kahrendt/fix-batch-min-phoneme Michael Hansen 2024-02-27 11:00:29 -06:00
213d4d561a revert removing webrtcvad Kevin Ahrendt 2024-02-27 10:01:27 -05:00
172d7b5cae use phoneme lengths to trim Kevin Ahrendt 2024-02-24 16:03:56 -05:00
315e555f49 Add pad after bos Michael Hansen 2024-02-05 14:18:15 -06:00
2dbff77c61 Add --min-phoneme-count Michael Hansen 2024-02-05 14:07:29 -06:00
77d8c0d4b3 Add configs for mls models Michael Hansen 2024-02-03 11:05:58 -06:00
195e3bd967 Clean up merge v2.0.0 Michael Hansen 2023-10-06 12:10:43 -05:00
595536c630 Merge remote-tracking branch 'dscripka/master' Michael Hansen 2023-10-06 12:00:28 -05:00
48e54922df Switch to libritts_r medium model and use piper-phonemize Michael Hansen 2023-10-06 11:56:57 -05:00
f1988a4d54 Added use of pywebrtc to remove excessive silence from generated clips dscripka 2023-09-11 07:56:17 -04:00
b104c2412d Fixed major bug where batch sizes >= 1 would not generate all input texts dscripka 2023-09-10 15:11:45 -04:00
28979b8964 Added functionality in 'generate_samples' function to attempt to auto-recover from CUDA OOM errors dscripka 2023-08-16 21:44:51 -04:00
8544faa48c typo dscripka 2023-08-06 11:20:34 -04:00
f82afc6596 Added example of import usage to README dscripka 2023-08-06 11:19:56 -04:00
8b4b20b712 Cleanup and verbose argument dscripka 2023-08-06 11:09:39 -04:00
a1f84c5ec3 Refactor to allow for usage of generation within Python script, added automatic resampling to 16khz dscripka 2023-06-20 07:35:39 -04:00
87f249822f Add --max-speakers Michael Hansen 2023-05-17 16:34:27 -05:00
b87c930fa1 Add download link Michael Hansen 2023-05-17 12:09:42 -05:00
d8aa042b96 Add impulses and rest of code v1.0.0 Michael Hansen 2023-05-17 12:02:34 -05:00
6ecc5192d9 Initial commit Michael Hansen 2023-05-16 17:06:57 -05:00