Bikkies/tortoise-tts
1
0
Fork 0
forked from mrq/tortoise-tts
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Commit Graph

  • 64ae4bb563 Updated setup scripts to use cuda 11.8 and torch 2.0.0 to fix RTX 4090 compatibility Added API to the generate function, so it can be called from other scripts 4090-cuda-and-api Bikkies 2023-02-11 19:46:26 +1100
  • 9bf1ea5b0a History tab (3/10 it works) main mrq 2023-02-11 01:45:25 +0000
  • 340a89f883 Numbering predicates on input_#.json files instead of "number of wavs" mrq 2023-02-10 22:51:56 +0000
  • 8641cc9906 revamped result formatting, added "kludgy" stop button mrq 2023-02-10 22:12:37 +0000
  • 8f789d17b9 Slight notebook adjust mrq 2023-02-10 20:22:12 +0000
  • 7471bc209c Moved voices out of the tortoise folder because it kept being processed for setup.py mrq 2023-02-10 20:11:56 +0000
  • 2bce24b9dd Cleanup mrq 2023-02-10 19:55:33 +0000
  • 811539b20a Added the remaining input settings mrq 2023-02-10 16:47:57 +0000
  • f5ed5499a0 Added a link to the colab notebook mrq 2023-02-10 16:26:13 +0000
  • 07c54ad361 Colab notebook (part II) mrq 2023-02-10 16:12:11 +0000
  • 939c89f16e Colab notebook (part 1) mrq 2023-02-10 15:58:56 +0000
  • 39b81318f2 Added new options: "Output Sample Rate", "Output Volume", and documentation mrq 2023-02-10 03:02:09 +0000
  • 77b39e59ac oops mrq 2023-02-09 22:17:57 +0000
  • 3621e16ef9 Added 'Only Load Models Locally' setting mrq 2023-02-09 22:06:55 +0000
  • dccedc3f66 Added and documented mrq 2023-02-09 21:07:51 +0000
  • 8c30cd1aa4 Oops mrq 2023-02-09 20:49:22 +0000
  • d7443dfa06 Added option: listen path mrq 2023-02-09 20:42:38 +0000
  • 38ee19cd57 I didn't have to suck off a wizard for DirectML support (courtesy of https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/7600 for leading the way) mrq 2023-02-09 05:05:21 +0000
  • 716e227953 oops mrq 2023-02-09 02:39:08 +0000
  • a37546ad99 owari da... mrq 2023-02-09 01:53:25 +0000
  • 6255c98006 beginning to add DirectML support mrq 2023-02-08 23:03:52 +0000
  • d9a9fa6a82 Added two flags/settings: embed output settings, slimmer computed voice latents mrq 2023-02-08 14:14:28 +0000
  • f03b6b8d97 disable telemetry/what-have-you if not requesting a public Gradio URL mrq 2023-02-07 21:44:16 +0000
  • 479f30c808 Merge pull request 'Added convert.sh' (#8) from lightmare/tortoise-tts:convert_sh into main mrq 2023-02-07 21:09:00 +0000
  • 40f52fa8d1 Added convert.sh lightmare 2023-02-07 20:43:13 +0000
  • 6ebdde58f0 (finally) added the CVVP model weigh slider, latents export more data too for weighing against CVVP mrq 2023-02-07 20:55:56 +0000
  • 793515772a un-hardcoded input output sampling rates (changing them "works" but leads to wrong audio, naturally) mrq 2023-02-07 18:34:29 +0000
  • 5f934c5feb (maybe) fixed an issue with using prompt redactions (emotions) on CPU causing a crash, because for some reason the wav2vec_alignment assumed CUDA was always available mrq 2023-02-07 07:51:05 -0600
  • d6b5d67f79 forgot to auto compute batch size again if set to 0 mrq 2023-02-06 23:14:17 -0600
  • 66cc6e2791 changed ROCm pip index URL from 5.2 to 5.1.1, because it's what worked for me desu mrq 2023-02-06 22:52:40 -0600
  • 6515d3b6de added shell scripts for linux, wrapped sorted() for voice list, I guess mrq 2023-02-06 21:54:31 -0600
  • edd642c3d3 fixed combining audio, somehow this broke, oops mrq 2023-02-07 00:26:22 +0000
  • be6fab9dcb added setting to adjust autoregressive sample batch size mrq 2023-02-06 22:31:06 +0000
  • 100b4d7e61 Added settings page, added checking for updates (disabled by default), some other things that I don't remember mrq 2023-02-06 21:43:01 +0000
  • 240858487f Added encoding and ripping latents used to generate the voice mrq 2023-02-06 16:32:09 +0000
  • 92cf9e1efe Added tab to read and copy settings from a voice clip (in the future, I'll see about enmbedding the latent used to generate the voice) mrq 2023-02-06 16:00:44 +0000
  • 5affc777e0 added another (somewhat adequate) example, added metadata storage to generated files (need to add in a viewer later) mrq 2023-02-06 14:17:41 +0000
  • b441a84615 added flag (--cond-latent-max-chunk-size) that should restrict the maximum chunk size when chunking for calculating conditional latents, to avoid OOMing on VRAM mrq 2023-02-06 05:10:07 +0000
  • a1f3b6a4da fixed up the computing conditional latents mrq 2023-02-06 03:44:34 +0000
  • 2cfd3bc213 updated README (before I go mad trying to nitpick and edit it while getting distracted from an iToddler sperging) mrq 2023-02-06 00:56:17 +0000
  • 945136330c Forgot to rename the cached latents to the new filename mrq 2023-02-05 23:51:52 +0000
  • 5bf21fdbe1 modified how conditional latents are computed (before, it just happened to only bother reading the first 102400/24000=4.26 seconds per audio input, now it will chunk it all to compute latents) mrq 2023-02-05 23:25:41 +0000
  • f66754b557 oops mrq 2023-02-05 20:10:40 +0000
  • 1c582b5dc8 added button to refresh voice list, enabling KV caching for a bonerific speed increase (credit to https://github.com/152334H/tortoise-tts-fast/) mrq 2023-02-05 17:59:13 +0000
  • 8831522de9 New tunable: pause size/breathing room (governs pause at the end of clips) mrq 2023-02-05 14:45:51 +0000
  • c7f85dbba2 Fix to keep prompted emotion for every split line mrq 2023-02-05 06:55:09 +0000
  • 79e0b85602 Updated .gitignore (that does not apply to me because I have a bad habit of having a repo copy separate from a working copy) mrq 2023-02-05 06:40:50 +0000
  • bc567d7263 Skip combining if not splitting, also avoids reading back the audio files to combine them by keeping them in memory mrq 2023-02-05 06:35:32 +0000
  • bf32efe503 Added multi-line parsing mrq 2023-02-05 06:17:51 +0000
  • cd94cc8459 Fixed accidentally not passing user-provided samples/iteration values (oops), fixed error thrown when trying to write unicode because python sucks mrq 2023-02-05 05:51:57 +0000
  • cab32e1f45 Forgot to add steps=1 to Candidates slider mrq 2023-02-05 04:27:20 +0000
  • 84a9758ab9 Set transformer and model folder to local './models/' instead of for the user profile, because I'm sick of more bloat polluting my C:\ mrq 2023-02-05 04:18:35 +0000
  • d29ba75dd6 cleaned up element order with Blocks, also added preset updating the samples/iterations counts mrq 2023-02-05 03:53:46 +0000
  • ed33e34fcc Added choices to choose between diffusion samplers (p, ddim) mrq 2023-02-05 01:28:31 +0000
  • 5c876b81f3 Added small optimization with caching latents, dropped Anaconda for just a py3.9 + pip + venv setup, added helper install scripts for such, cleaned up app.py, added flag '--low-vram' to disable minor optimizations mrq 2023-02-04 01:50:57 +0000
  • 8f20afc18f Reverted slight improvement patch, as it's just enough to OOM on GPUs with low VRAM mrq 2023-02-03 21:45:06 +0000
  • e8d4a4f89c Added progress for transforming to audio, changed number inputs to sliders instead mrq 2023-02-03 04:56:30 +0000
  • ea751d7b6c forgot to copy the alleged slight performance improvement patch, added detailed progress information with passing gr.Progress, save a little more info with output mrq 2023-02-03 04:20:01 +0000
  • 43f45274dd Cleaned up the good-morning-sirs-dialect labels, fixed seed=0 not being a random seed, show seed on output mrq 2023-02-03 01:25:03 +0000
  • 74f447e5d0 QoL fixes mrq 2023-02-02 21:13:28 +0000
  • f6be2a3ee8 Quick fixes for Conda mrq 2023-02-01 01:21:56 +0000
  • 8d342cfbc0
         Merge pull request #263 from netshade/remove-ffmpeg-dep James Betker 2023-01-22 17:55:36 -0700
  • e55b498239 remove ffmpeg requirement, not actually necessary chris 2023-01-22 16:41:25 -0500
  • 5dc3e269b3
         Merge pull request #233 from kianmeng/fix-typos James Betker 2023-01-17 18:24:24 -0700
  • b5eec7aba3
         Merge pull request #245 from netshade/installation-updates James Betker 2023-01-11 09:30:50 -0700
  • 7ce3dc7bf1 add explicit requirements.txt usage for dep installation chris 2023-01-11 10:50:18 -0500
  • d999f55841 update requirements to ensure project will build and run chris 2023-01-11 10:48:58 -0500
  • 217dc09d5f
         Merge pull request #234 from Wonbin-Jung/ack James Betker 2023-01-06 02:03:49 -0700
  • b3d67dcc6b Add reference of univnet implementation 원빈 정 2023-01-06 15:57:02 +0900
  • 551fe655ff Fix typos Kian-Meng Ang 2023-01-05 19:49:55 +0800
  • 2c0d8d71e0
         Merge pull request #229 from Livshitz/patch-1 James Betker 2023-01-02 13:05:34 -0700
  • 7bc068ca5a
         Update tortoise_v2_examples.html Elya Livshitz 2023-01-02 19:45:11 +0200
  • f28a116b48
         Update README.md James Betker 2022-12-05 13:16:36 -0800
  • 121b0e9e9c
         Merge pull request #193 from casonclagg/main James Betker 2022-11-13 22:20:11 -0800
  • 6587d1934e Pin transformers version to 4.19, fixes #186, google colab crashing Cason Clagg 2022-11-11 17:16:56 -0600
  • 122d92d491
         Merge pull request #122 from mogwai/fix/readme-instructions James Betker 2022-07-08 08:22:43 -0600
  • 2efc5a3e50 Added keyword argument Harry Coultas Blum 2022-07-08 14:28:24 +0100
  • 00f8bc5e78
         Update README.md James Betker 2022-06-23 15:57:50 -0700
  • 958c6d2f73 Get rid of checkpointing James Betker 2022-06-15 22:09:15 -0600
  • 29c1d9e561
         Merge pull request #97 from jnordberg/cpu-support James Betker 2022-06-12 23:12:03 -0600
  • de7c5ddec3 Typofix Johan Nordberg 2022-06-11 21:00:16 +0900
  • fc4a31028a Expose batch size and device settings in CLI Johan Nordberg 2022-06-11 20:46:23 +0900
  • b876a6b32c Allow running on CPU Johan Nordberg 2022-06-11 20:03:14 +0900
  • a9e64e216d
         Merge pull request #90 from MarcusLlewellyn/read_combine James Betker 2022-06-06 14:59:35 -0600
  • 700978b777 Fixed silly lack of EOF blank line, indentation Marcus Llewellyn 2022-06-06 15:13:29 -0500
  • 2477a4f763 read.py combines all candidates Marcus Llewellyn 2022-06-04 17:47:29 -0500
  • 480f7e37d9 Also include voices in the manifest James Betker 2022-05-31 10:31:50 -0600
  • 48fe3288fe Include data in manifest James Betker 2022-05-31 09:10:06 -0600
  • 780d2ce313
         Merge pull request #78 from jnordberg/cli-typo-fix James Betker 2022-05-28 22:30:41 -0600
  • b73d46e811 Typofix Johan Nordberg 2022-05-29 04:26:11 +0000
  • 68c1580f94
         Merge pull request #74 from jnordberg/improved-cli James Betker 2022-05-28 21:33:53 -0600
  • d8f98c07b4 Remove some assumptions about working directory This allows cli tool to run when not standing in repository dir Johan Nordberg 2022-05-29 01:10:19 +0000
  • 870b2d2fc2
         Merge pull request #70 from jnordberg/sentence-split-improve James Betker 2022-05-28 11:03:43 -0600
  • 9f6ae0f0b3 Add tortoise_cli.py Johan Nordberg 2022-05-28 05:25:23 +0000
  • 561ae9a31e Typofix Johan Nordberg 2022-05-28 01:29:34 +0000
  • 6a71d90316 Improve splitting on text that has many quotes Johan Nordberg 2022-05-28 01:22:21 +0000
  • f199d6b85c Add riding hood test Also fix a bug discovered by the test that would seek past the text end if it ended in a boundary Johan Nordberg 2022-05-27 23:08:53 +0000
  • b294f0217f Improve sentence boundary detection Johan Nordberg 2022-05-27 05:58:09 +0000
  • 3f7386d442
         Merge pull request #68 from space-pope/fix-default-arg James Betker 2022-05-26 15:59:43 -0600
  • 5b0e50eaa6
         avoid mutable default in aligner Josh Ziegler 2022-05-26 16:20:09 -0400