oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-01-03 23:30:06 +01:00
Code Issues Actions Packages Projects Releases Wiki Activity
698 commits 6 branches 91 tags 66 MiB
Commit graph

698 commits

This branch
This branch
All branches
Author SHA1 Message Date
Xan b8f7d34c1d Undo changes to requirements 
needing to manually install tensorboard might be a windows-only problem. Can be easily solved manually.
 2023-03-11 17:05:09 +11:00
Xan 0dfac4b777 Working html autoplay, clean up, improve wav naming 
- New autoplay using html tag, removed from old message when new input provided
- Add voice pitch and speed control
- Group settings together
- Use name + conversation history to match wavs to messages, minimize problems when changing characters

Current minor bugs:
- Gradio seems to cache the audio files, so using "clear history" and generating new messages will play the old audio (the new messages are saving correctly). Gradio will clear cache and use correct audio after a few messages or after a page refresh.
- Switching characters does not immediately update the message ID used for the audio. ID is updated after the first new message, but that message will use the wrong ID
 2023-03-11 16:34:59 +11:00
Xan a2b5383398 Merge in audio generation only on text stream finish., postpone audioblock autoplay 
- Keeping simpleaudio until audio block "autoplay" doesn't play previous messages
- Only generate audio for finished messages
- Better name for autoplay, clean up comments
- set default to unlimited wav files. Still a few bugs when wav id resets

Co-Authored-By: Christoph Hess <9931495+ChristophHess@users.noreply.github.com>
 2023-03-09 10:48:44 +11:00
Xan 738be6dd59 Fix merge errors and unlimited wav bug 2023-03-08 22:25:55 +11:00
Xan 5648a41a27 Merge branch 'main' of https://github.com/xanthousm/text-generation-webui 2023-03-08 22:08:54 +11:00
Xan ad6b699503 Better TTS with autoplay 
- Adds "still_streaming" to shared module for extensions to know if generation is complete
- Changed TTS extension with new options:
   - Show text under the audio widget
   - Automatically play the audio once text generation finishes
   - manage the generated wav files (only keep files for finished generations, optional max file limit)
   - [wip] ability to change voice pitch and speed
- added 'tensorboard' to requirements, since python sent "tensorboard not found" errors after a fresh installation.
 2023-03-08 22:02:17 +11:00
oobabooga c09f416adb Change the Naive preset 
(again)
 2023-03-07 23:17:13 -03:00
oobabooga 8e89bc596b Fix encode() for RWKV 2023-03-07 23:15:46 -03:00
oobabooga 44e6d82185 Remove unused imports 2023-03-07 22:56:15 -03:00
oobabooga 19a34941ed Add proper streaming to RWKV 2023-03-07 18:17:56 -03:00
oobabooga 8660227e1b Add top_k to RWKV 2023-03-07 17:24:28 -03:00
oobabooga 827ae51f72
Sort the imports 2023-03-07 00:23:36 -03:00
oobabooga b4bfd87319
Update README.md 2023-03-06 20:55:01 -03:00
oobabooga 8f4a197c05
Add credits 2023-03-06 20:34:36 -03:00
oobabooga d0e8780555
Update README.md 2023-03-06 20:17:59 -03:00
oobabooga 18eaeebbfe Merge branch 'main' of github.com:oobabooga/text-generation-webui 2023-03-06 20:16:03 -03:00
oobabooga 18ccfcd7fe
Update README.md 2023-03-06 20:15:55 -03:00
oobabooga 153dfeb4dd Add --rwkv-cuda-on parameter, bump rwkv version 2023-03-06 20:12:54 -03:00
oobabooga 4143d4aa48
Merge pull request #175 from SagsMug/main 
Add api example using websockets
 2023-03-06 19:53:48 -03:00
oobabooga 8b882c132a
tabs -> spaces 2023-03-06 19:52:26 -03:00
oobabooga eebec65075 Improve readability 2023-03-06 19:46:46 -03:00
oobabooga 99f69dfcaa
Merge pull request #169 from MetaIX/patch-1 
Support for Eleven Labs TTS
 2023-03-06 19:40:31 -03:00
oobabooga 944fdc03b2 Rename the folder 2023-03-06 19:38:36 -03:00
oobabooga 49ae183ac9 Move new extension to a separate file 2023-03-06 19:28:53 -03:00
oobabooga 91823e1ed1
Update README.md 2023-03-06 16:48:31 -03:00
oobabooga 6904a507c6 Change some parameters 2023-03-06 16:29:43 -03:00
oobabooga 20bd645f6a Fix bug in multigpu setups (attempt 3) 2023-03-06 15:58:18 -03:00
oobabooga 09a7c36e1b Minor improvement while running custom models 2023-03-06 15:36:35 -03:00
oobabooga 24c4c20391 Fix bug in multigpu setups (attempt #2) 2023-03-06 15:23:29 -03:00
oobabooga d88b7836c6 Fix bug in multigpu setups 2023-03-06 14:58:30 -03:00
oobabooga 5bed607b77 Increase repetition frequency/penalty for RWKV 2023-03-06 14:25:48 -03:00
oobabooga aa7ce0665e Merge branch 'main' of github.com:oobabooga/text-generation-webui 2023-03-06 10:58:41 -03:00
oobabooga bf56b6c1fb Load settings.json without the need for --settings settings.json 
This is for setting UI defaults
 2023-03-06 10:57:45 -03:00
oobabooga 2de9f122cd
Update README.md 2023-03-06 09:34:49 -03:00
oobabooga e91f4bc25a Add RWKV tokenizer 2023-03-06 08:45:49 -03:00
Mug 53ce21ac68 Add api example using websockets 2023-03-06 12:13:50 +01:00
MetaIX 9907bee4a4
Support for Eleven Labs TTS 
As per your suggestion at https://github.com/oobabooga/text-generation-webui/issues/159 here's my attempt.

I'm brand new to python and github. Completely different from unreal + visual coding, so forgive my amateurish code. This essentially adds support for Eleven Labs TTS. Tested it without major issues, and I believe it's functional (hopefully).

Extra requirements: elevenlabslib https://github.com/lugia19/elevenlabslib, sounddevice0.4.6, and soundfile

Folder structure is the same as the SileroTTS Extension.
 2023-03-05 19:04:22 -06:00
oobabooga c855b828fe Better handle <USER> 2023-03-05 17:01:47 -03:00
oobabooga 145c725c39 Bump RWKV version 2023-03-05 16:28:21 -03:00
oobabooga 2af66a4d4c Fix <USER> in pygmalion replies 2023-03-05 16:08:50 -03:00
oobabooga a54b91af77 Improve readability 2023-03-05 10:21:15 -03:00
oobabooga 8e706df20e Fix a memory leak when text streaming is on 2023-03-05 10:12:43 -03:00
oobabooga 5492e2e9f8 Add sentencepiece 2023-03-05 10:02:24 -03:00
oobabooga 90206204aa
Merge pull request #163 from oobabooga/hf_llama 
Move towards HF LLaMA implementation
 2023-03-05 01:55:43 -03:00
oobabooga c33715ad5b Move towards HF LLaMA implementation 2023-03-05 01:20:31 -03:00
oobabooga bd8aac8fa4 Add LLaMA 8-bit support 2023-03-04 13:28:42 -03:00
oobabooga c93f1fa99b Count the tokens more conservatively 2023-03-04 03:10:21 -03:00
oobabooga 736f61610b Update README 2023-03-04 01:33:52 -03:00
oobabooga ed8b35efd2 Add --pin-weight parameter for FlexGen 2023-03-04 01:04:02 -03:00
oobabooga 05e703b4a4 Print the performance information more reliably 2023-03-03 21:24:32 -03:00