lightmare created pull request mrq/ai-voice-cloning#76
WIP: Added experimental guided setuplightmare pushed to guided-setup at lightmare/ai-voice-cloning
- 2c244c49ec Added experimental guided setup
- 119ac50c58 forgot to re-append the existing transcription when skipping existing (have to go back again and do the first 10% of my giant dataset
- da0af4c498 one more
- 11a1f6a00e forgot to reorder the dependency install because whisperx needs to be installed before DLAS
- 12c51b6057 Im not too sure if manually invoking gc actually closes all the open files from whisperx (or ROCm), but it seems to have gone away longside setting 'ulimit -Sn' to half the output of 'ulimit -Hn'
- Compare 10 commits »
lightmare pushed tag v1.2.0 to lightmare/whispercpp.py
lightmare pushed to main at lightmare/whispercpp.py
- 7b6fa0d819 release 1.2.0
- cc9c123251 Added new extraction and trimming functionality
- Compare 2 commits »
lightmare commented on issue mrq/ai-voice-cloning#37
[Feature request] Add support for whisper.cpp> I tried the other day on Windows but absolutely couldn't get it to be happy. I imagine if it's giving me hell, it'd be hell for any other Windows user to try and get it to compile anyhow. Oh…
lightmare created pull request mrq/ai-voice-cloning#57
Added optional whispercpp update functionalitylightmare pushed to whispercpp-update at lightmare/ai-voice-cloning
- 5487c28683 Added optional whispercpp update functionality
- 9fb4aa7917 validated whispercpp working, fixed args.listen not being saved due to brainworms
- 740b5587df added option to specify using BigVGAN as the vocoder for mrq/tortoise-tts
- 68f4858ce9 oops
- e859a7c01d experimental multi-gpu training (Linux only, because I can't into batch files)
- Compare 10 commits »
lightmare pushed tag v1.1.0 to lightmare/whispercpp.py
lightmare pushed to main at lightmare/whispercpp.py
- 2a4f9b3e40 release 1.1.0
lightmare pushed to main at lightmare/whispercpp.py
- d6c4748424 Clarified documentation
lightmare pushed to main at lightmare/whispercpp.py
- d14f1b6c25 whisper.cpp v1.2.1
lightmare commented on issue mrq/ai-voice-cloning#47
ERROR: Could not open requirements file: [Errno 2] No such file or directory:> This may seem like a dumb question but how exactly do I get the full stack trace? Basically everything that was printed to the console when you executed the script.
lightmare commented on issue mrq/ai-voice-cloning#37
[Feature request] Add support for whisper.cpp> Forgot to mention I think yesterday when I remembered to commit it: added support for it in commit 6925ec731baebf08de3fc81368559e08684c047f. Very nice, thank you. > Although, I couldn't…
lightmare opened issue mrq/ai-voice-cloning#37
[Feature request] Add support for whisper.cpplightmare pushed to main at lightmare/whispercpp.py
- d5eb133526 Fixed `print_system_info`
lightmare pushed to main at lightmare/whispercpp.py
- 5a4f948785 Added `list_languages` function
- b0795baa43 Added `token_timestamps` and `print_timestamps` params
- Compare 2 commits »
lightmare pushed to main at lightmare/whispercpp.py
- 12340d769f Added `extract_text_and_timestamps` method
- 765c02ec87 Fixed docstring
- 2854cdfbe3 Fixed n_threads param
- Compare 3 commits »