Commit graph

47 commits

Author SHA1 Message Date
James Betker 053b8d138a remove xt dep 2022-04-20 18:00:12 -06:00
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