Commit Graph
542 Commits
Author SHA1 Message Date
erew123 e3878b595b Update requirements_googlecolab.txt 2024-03-28 23:25:34 +00:00
erew123 825e4a7d12 Add files via upload 2024-03-28 23:14:02 +00:00
erew123 6c20f45154 Add files via upload 1.9c 2024-03-28 21:51:42 +00:00
erew123 97cda27c7e Delete finetune/put-voice-samples-in-here directory 2024-03-28 21:51:11 +00:00
erew123 a075495a0a Large Update
TTS Generator - Various interface bugs & filtering options cleaned up.
TTS Generator - TTSDiff now scans generated text and TTS for errors.
TTS Generator - TTSSRT now creates subtitle files for video production e.g. a Youtube video.
Finetune - Now uses a customised tokenizer to deal with Japanese.
Finetune - Pre flight check and warning messages.
Finetune - Extra documentation and warnings.
Entire file structure has been re-organised to simplify management and future changes.
Documentation (built in and Github) has been rewritten/tidied up.
Requirements files have been cleaned up and simplified.
ATsetup has been re-written as necessary with additional options.
DeepSpeed moved up to version 14.
Standalone Application moved to PyTorch 2.2.1.
Nvidia CUDA Toolkit installation is NO LONGER needed (other than to compile DeepSpeed on Linux)

Tested on Linux and Windows.
2024-03-28 21:49:33 +00:00
erew123 b205657be3 Delete finetune/compact.py 2024-03-28 21:38:03 +00:00
erew123 483d6c8e79 Delete harvard_sentences.txt 2024-03-28 21:37:52 +00:00
erew123 9bd4665e6b Delete languages.json 2024-03-28 21:37:45 +00:00
erew123 62e1ab7e89 Delete requirements_other.txt 2024-03-28 21:37:35 +00:00
erew123 740c54db1c Delete requirements_nvidia.txt 2024-03-28 21:37:27 +00:00
erew123 e188467730 Delete requirements_finetune.txt 2024-03-28 21:37:12 +00:00
erew123 743f23240e Delete templates directory 2024-03-28 21:36:51 +00:00
erew123 66dadbca25 Finetune - further tidy up
Amended instructions.
Tidied up Pre-Flight check.
Added  dropdowns refresh button for step 3.
2024-03-25 14:09:35 +00:00
erew123 8125b46dbe Update README.md 2024-03-24 14:38:08 +00:00
erew123 d4bd46f203 Update README.md 2024-03-24 14:00:14 +00:00
erew123 f13d6d336b Update README.md 2024-03-24 11:37:33 +00:00
erew123 1fa2f2e110 Update README.md 2024-03-24 11:16:45 +00:00
erew123 9ad4005e52 Update bug-report-support-request.md 2024-03-23 23:06:59 +00:00
erew123 6d6b92d4b2 Update README.md 2024-03-23 12:18:09 +00:00
erew123 bf5d913cae Delete Deepspeed-Windows directory 2024-03-23 12:03:21 +00:00
erew123 f52ccd3931 Update README.md 2024-03-23 11:57:13 +00:00
erew123 37e7c8002d Update README.md 2024-03-22 17:23:12 +00:00
erew123 ad7382ee68 Update README.md 2024-03-22 14:53:28 +00:00
erew123 2428bfe357 Update README.md 2024-03-22 13:59:00 +00:00
erew123 74f3acc51f Update README.md
Large documentation update
2024-03-22 13:53:28 +00:00
erew123 90a98f140b Update ttsgencomp.py 2024-03-20 16:56:59 +00:00
erew123 885311ecd8 ttsgencomp added --threshold
gives a little flexibility to deal with words that sound the same when transcribed.
2024-03-20 16:28:15 +00:00
erew123 c2952e9758 Add files via upload 2024-03-20 15:50:02 +00:00
erew123 7e6e18c6d9 TTSGEN Compare - Work in progress
A BETA test/Proof of concept script to compare Speech that was generated in TTS Generator to the original Text and flag issues.

Anyone reading this, you are welcome to try it, the readme instructions are in the folder, however, I am not providing support on this while it is BETA/Proof of concept.
2024-03-20 15:26:36 +00:00
erew123 47eafafeda Update README.md 2024-03-19 12:35:15 +00:00
erew123 5edaab1356 Update README.md 2024-03-19 12:20:44 +00:00
erew123 7bde34d2ce Update README.md 2024-03-19 12:03:32 +00:00
erew123 0aa4638f68 Update README.md 2024-03-19 11:54:50 +00:00
erew123 22dd9c741c Update README.md 2024-03-19 11:51:03 +00:00
erew123 e000b8bb87 Update README.md 2024-03-19 11:10:00 +00:00
erew123 2d26f309df Update README.md 2024-03-19 11:06:04 +00:00
erew123 22d3e53a28 Update bug-report-support-request.md 2024-03-19 10:42:56 +00:00
erew123 0ea646dbf3 Update bug-report-support-request.md 2024-03-19 10:41:42 +00:00
erew123 282e3ce84c Update bug-report-support-request.md 2024-03-19 10:41:04 +00:00
erew123 772afd47a1 Update README.md 2024-03-19 10:11:29 +00:00
erew123 1612835c5d Update README.md 2024-03-19 09:55:50 +00:00
erew123 ea551d3a84 ID Playing reset on stop - corrected
Corrected the ID playing from resetting when the Stop button is pressed.
2024-03-17 12:51:41 +00:00
erew123 47001203cd Added DeepSpeed v14 for CUDA 11.8 w/PT 2.2.1 2024-03-16 13:21:25 +00:00
erew123 27ff5a12b0 Delete templates/tokenizer/__pycache__ directory 2024-03-16 11:16:01 +00:00
erew123 0a89407e4d Custom tokenizer for Japanese
Replaces the standard TTS tokenizer within Finetuning.
2024-03-16 11:15:01 +00:00
erew123 a579c5e6d2 Additional checks, documentation & tokenizer
Added warnings if PFC is not passed.
Added a custom tokenizer to better handle Japanese.
2024-03-16 11:14:07 +00:00
erew123 5a21d14672 Update atsetup.bat
TTS version updated to 0.22.0
2024-03-16 02:35:58 +00:00
erew123 f4f5f82bb0 Update atsetup.sh
TTS version updated to 0.22.0
2024-03-16 02:35:39 +00:00
erew123 7b03804f9e Finetune updated
Now uses TTS 0.22.0
Pre-flight check system & help documentation.
Cleaned up the interface a little
More yet to do re documentation.
2024-03-16 02:34:17 +00:00
erew123 f46493e6d8 Updated diagnostic checks
Added a few additional checks
Simplified screen output
Cleaned up log file output
2024-03-15 02:14:58 +00:00