erew123
1f0cf09822
Update requirements_colab.txt
2024-08-09 08:36:29 +01:00
erew123
526e71a46e
Update requirements_textgen.txt
2024-08-09 08:35:59 +01:00
erew123
569b4a7403
PIP requirements. Merge pull request #301 from IIEleven11/cloud_instance
...
Update requirements_standalone.txt
2024-08-09 08:33:48 +01:00
IIEleven11
4494ef24c0
Update requirements_standalone.txt
...
Not sure what happened but all of a sudden this stopped working. I chased the dep issues down and fixed the wildcard * with >< operators issue
2024-08-09 00:21:13 -07:00
erew123
cf93ef1de0
Merge pull request #299 from bmalaski/fixexport
...
BUGFIX: Exporting Model after Restart
2024-08-08 08:38:12 +01:00
Bryant21
98d4d4fd25
BUGFIX: Exporting Model after Restart
2024-08-07 23:38:41 -04:00
erew123
2560c29771
Updated dropdown size after Distil added
2024-08-04 18:54:06 +01:00
erew123
0be7eae436
Merge pull request #295 from bmalaski/distiled
...
Add distil-large-v3 for dataset creation
2024-08-04 18:52:49 +01:00
Bryant21
6b43c40a8c
Update finetune.py
2024-08-04 13:33:53 -04:00
Bryant21
94c9257dee
change default to distil
2024-08-04 13:27:42 -04:00
Bryant21
eaf38309a2
Update finetune.py
2024-08-04 13:22:51 -04:00
erew123
bf68a89c11
/api/openai-voicemap API endpoint
...
Can call /api/openai-voicemap with
curl -X PUT "http://localhost:7851/api/openai-voicemap " -H "Content-Type: application/json" -d "{\"alloy\":\"female_01.wav\",\"echo\":\"female_01.wav\",\"fable\":\"female_01.wav\",\"nova\":\"female_01.wav\",\"onyx\":\"male_01.wav\",\"shimmer\":\"male_02.wav\"}"
Caveats:
- You have to update all the voices in one go, not just one voice.
- Its up to you to ensure you have the correct voices for the TTS engine that's loaded in which you can find currently available on /api/voices
- The in-memory mappings will update, but Gradio will have cached what was originally in the settings, so it wont display the changes in the Gradio interface without a restart of AllTalk/Gradio
2024-07-28 08:52:00 +01:00
erew123
5257497b57
Notes/warning on docker like environments
2024-07-27 09:17:20 +01:00
erew123
6fac1aa5f9
Additional Instructions.
2024-07-27 09:05:03 +01:00
erew123
4c97c83d25
Added additional instructions
2024-07-27 08:46:29 +01:00
erew123
61e6c2c105
downgrade pip version
...
python -m pip install --upgrade "pip<24.1"
Due to how the new pip handles requirements
2024-07-27 07:40:19 +01:00
erew123
0755aa033b
googlecolab downgrade pip
...
python -m pip install --upgrade "pip<24.1"
2024-07-27 07:38:38 +01:00
erew123
fe44f3608a
atsetup.bat silent install option
...
-silent command line switch.
2024-07-26 07:44:55 +01:00
erew123
f1c53866ba
Czech & Turkish character set
2024-07-22 09:42:22 +01:00
erew123
a9fc8699d8
Extend base API config for Czech & Turkish
2024-07-22 09:01:45 +01:00
erew123
e63b882e52
Extend admin.html character set for TTS
2024-07-21 18:35:35 +01:00
erew123
21064be53a
Update finetune.py
2024-07-21 18:10:56 +01:00
erew123
c03ab37dd2
Finetune - Allow number of workers selection
2024-07-21 17:31:52 +01:00
erew123
b03e08405e
Update clipboard-to-tts.py
2024-07-17 13:41:38 +01:00
erew123
c31e1f68b5
Update instructions.txt
2024-07-16 16:25:47 +01:00
erew123
d542e6ba14
Clipboard to TTS
...
A very rough bit of code for Windows to generate TTS from any text sent to the WINDOWS clipboard with Ctrl+C
2024-07-16 16:21:40 +01:00
erew123
0f26ca4bbf
API address changes apply correctly
2024-07-13 21:49:37 +01:00
erew123
16152fe135
Added trainer to requirements
2024-07-13 07:19:19 +01:00
erew123
f03f359f41
Merge pull request #255 from bmalaski/alltalkbeta_enhancements
...
Alltalkbeta enhancements - Finetuning
2024-07-13 07:11:22 +01:00
erew123
e40470fbea
Improve diags on systems with no CUDA
2024-07-05 08:31:40 +01:00
bmalaski
d5c20262a8
Update WarmUpScheduler.py
2024-07-04 22:18:28 -04:00
bmalaski
6a992cb8f4
Update WarmUpScheduler.py
2024-07-03 09:59:25 -04:00
bmalaski
e347f15046
add warmup
2024-07-02 00:14:54 -04:00
erew123
41a059e517
Add files via upload
2024-07-01 09:56:09 +01:00
erew123
797a4b996a
Update finetune.py
2024-07-01 08:32:56 +01:00
bmalaski
e081442bf3
Update finetune.py
2024-06-25 15:49:20 -04:00
erew123
bccd7ee971
Update README.md
2024-06-24 09:27:58 +01:00
erew123
4cba3af3b5
Add files via upload
2024-06-22 16:02:12 +01:00
erew123
f016c6cd90
add condition on message
2024-06-22 15:17:12 +01:00
erew123
da767a5472
Update requirements_colab.txt
2024-06-22 14:51:40 +01:00
erew123
633113f909
Update requirements_textgen2.txt
2024-06-22 14:51:25 +01:00
erew123
45e3ed9237
Update requirements_standalone.txt
...
added Pillow
2024-06-22 14:51:06 +01:00
bmalaski
a97ad658c1
ported changes form original branch
2024-06-20 22:54:57 -04:00
bmalaski
062483df1a
start merge
2024-06-20 13:56:31 -04:00
erew123
92ce5e24bc
Update some error messages for Streaming.
2024-06-19 11:08:48 +01:00
erew123
b32c68df29
update default pitch
2024-06-17 20:59:16 +01:00
erew123
84312bb6b4
RVC Pitch on API
...
adds RVC pitch to the API and generate screen.
Still need to update TGWUI, SillyTavern Extensions along with documentation.
2024-06-17 11:42:54 +01:00
erew123
6f4bec7ab2
Extended TTS generation timeout in Gradio
...
extended the timeout to await a TTS generation response, just to help with Google colab
2024-06-13 12:21:08 +01:00
erew123
6f75ab9f60
WIP Google Colab workbook
...
This is a work in progress. There are issues to address:
- RVC does not work yet.
- There is a stutter on the 1st TTS generation.
- Transcoding damages the file in some way (seems to be a colab specific issue)
- First model selection and other configuration settings may need to be pre-set.
- Long TTS generations can timeout in Gradio interface, hence should be run on at least a T4 runtime.
2024-06-13 12:18:41 +01:00
erew123
50f335255e
Data validation/missing files printout @ console
2024-06-13 10:38:23 +01:00
erew123