Commit Graph

46 Commits

Author SHA1 Message Date
James Betker
0b496a0a38 update clvp path 2022-04-20 17:59:34 -06:00
James Betker
8696bb45b3 updates to scripts 2022-04-20 17:24:09 -06:00
James Betker
2bf7cd1101 y u no cvvp 2022-04-18 20:47:16 -06:00
James Betker
f01c9a2147 AND OTHER DEPS 2022-04-18 20:44:22 -06:00
James Betker
24a5b840ae remove dependency on x-transformers 2022-04-18 20:43:04 -06:00
James Betker
ad0f3fdd58 update to v2 models (clvp pending) 2022-04-18 17:32:54 -06:00
James Betker
a578697287 clear out new_autoregressive api 2022-04-18 14:48:08 -06:00
James Betker
8e94abd341 Support CVVP & fix for major bug in API 2022-04-18 14:47:44 -06:00
James Betker
39ab8a9adf yeah 2022-04-18 10:30:22 -06:00
James Betker
fc8d52a998 update do_tts 2022-04-18 10:22:36 -06:00
James Betker
76c30fe344 Update autoregressive to support type inputs 2022-04-18 10:22:05 -06:00
James Betker
713281e376 update api constants 2022-04-18 09:22:15 -06:00
James Betker
c52cc78632 update 2022-04-15 08:26:11 -06:00
James Betker
b4c568ab87 restore in-set voices 2022-04-15 08:25:46 -06:00
James Betker
979ff6e65e implement clip-guided generation (and never use it...) 2022-04-14 21:50:57 -06:00
James Betker
60d363fc60 new voices 2022-04-14 21:49:54 -06:00
James Betker
776e5634fd Remove intelligibility refinement
It's not longer a concern. :)
2022-04-13 17:04:19 -06:00
James Betker
56f8385b99 Update sweep & eval_multiple with new voices 2022-04-13 17:03:36 -06:00
James Betker
3214ca0dfe support latents into the diffusion decoder 2022-04-12 20:53:09 -06:00
James Betker
e2ee843098 Updates 2022-04-12 16:40:42 -06:00
James Betker
17af2df44f support presets for generation 2022-04-10 23:19:15 -06:00
James Betker
8215af8b9d Add read script 2022-04-10 19:29:42 -06:00
James Betker
b07fb37a78 Clip diffusion inputs 2022-04-10 19:29:32 -06:00
James Betker
b1ba8416ff Updates 2022-04-10 14:41:13 -06:00
James Betker
f37375bb72 updates for new autoregressive 2022-04-08 09:25:21 -06:00
James Betker
73e9929825 new autoregressive check-in 2022-04-07 22:18:56 -07:00
James Betker
33e4bc7907 integrate new autoregressive model and fix new diffusion bug 2022-04-04 16:51:35 -06:00
James Betker
9043dde3f9 Integrate new diffusion network 2022-04-01 14:15:17 -06:00
James Betker
287debd1d3 port do_tts to use the API 2022-04-01 11:55:07 -06:00
James Betker
9db06e139b param improvements from investigation 2022-04-01 11:34:40 -06:00
James Betker
cdc26b5e23 Add sweeper script for finding optimal generation hyperparameters. 2022-03-29 13:59:59 -06:00
James Betker
f625a9e443 Update API to have more expressive interface for controlling various generation knobs
- Also adds typical decoder support; unfortunately this does not work well with the current model.
2022-03-29 13:59:39 -06:00
James Betker
b78ae92890 Upgrade CLIP model and add eval_multiple 2022-03-28 19:33:31 -06:00
James Betker
c66954b6a6 Add in ASR filtration 2022-03-26 21:32:12 -06:00
James Betker
9ad0f0e6e8 Modifications to support "v1.5" 2022-03-22 11:52:46 -06:00
James Betker
31f7372024 Another update 2022-03-10 23:33:48 -07:00
James Betker
048b0996bc Update readme 2022-03-10 23:32:35 -07:00
James Betker
8effe3554b More updates 2022-03-10 23:21:16 -07:00
James Betker
56b10cc54c Add colab notebook 2022-03-10 23:21:01 -07:00
James Betker
54a946d0ae Some fixes 2022-03-10 22:56:29 -07:00
James Betker
8d035595be Update with downloadable model paths 2022-03-10 22:46:35 -07:00
James Betker
8655b05f36 Upload sample results and voices 2022-03-10 22:46:15 -07:00
James Betker
1a2fb5db63 Update docs 2022-02-03 22:18:21 -07:00
James Betker
c34f5edfd7 Some renaming 2022-01-27 23:21:44 -07:00
James Betker
5a958b4f4b Initial commit 2022-01-27 23:19:29 -07:00
James Betker
051f500010
Initial commit 2022-01-27 21:33:15 -07:00