Fetching metadata from the HF Docker repository... Iñaki Marin
More changes.
c853a45 unverified - bin Initial refractor
- models remove redundant phonemize for vall-e (oops), quantize all files and then phonemize all files for cope optimization, load alignment model once instead of for every transcription (speedup with whisperx)
- modules New Changes.
- results Initial refractor
- src modified logic to determine valid voice folders, also allows subdirs within the folder (for example: ./voices/SH/james/ will be named SH/james)
- training a bit of UI cleanup, import multiple audio files at once, actually shows progress when importing voices, hides audio metadata / latents if no generated settings are detected, preparing datasets shows its progress, saving a training YAML shows a message when done, training now works within the web UI, training output shows to web UI, provided notebook is cleaned up and uses a venv, etc.
- voices Initial refractor
- 8.2 kB More changes.
- 31 Bytes docker support
- 1.92 kB experimental multi-gpu training (Linux only, because I can't into batch files)
- 191 Bytes while I'm breaking things, migrating dependencies to modules folder for tidiness
- 1.47 kB docker: add ffmpeg for whisper and general cleanup
- 34.7 kB Initial refractor
- 1.38 kB Update README.md
- 5.27 kB share if you
- 3.02 kB fixed notebooks, provided paperspace notebook
- 118 Bytes setup bnb on windows as needed
- 382 Bytes setup bnb on windows as needed
- 585 Bytes DLAS is PIPified (but I'm still cloning it as a submodule to make updating it easier)
- 788 Bytes DLAS is PIPified (but I'm still cloning it as a submodule to make updating it easier)
- 512 Bytes DLAS is PIPified (but I'm still cloning it as a submodule to make updating it easier)
- 96 Bytes docker support
- 371 Bytes while I'm breaking things, migrating dependencies to modules folder for tidiness
- 799 Bytes DLAS is PIPified (but I'm still cloning it as a submodule to make updating it easier)
- 463 Bytes docker support
- 106 Bytes added PYTHONUTF8 to start/train bats
- 119 Bytes :)
- 646 Bytes docker: add training script
- 104 Bytes ;)
- 85 Bytes ;)
- 414 Bytes removed the hotfix pip installs that whisperx requires now that whisperx is gone
- 458 Bytes DLAS is PIPified (but I'm still cloning it as a submodule to make updating it easier)
- 39 Bytes added button to just load a training set's loss information, added installing broncotc/bitsandbytes-rocm when running setup-rocm.sh
- 220 Bytes added PYTHONUTF8 to start/train bats
