ai-voice-cloning/requirements.txt

--extra-index-url https://download.pytorch.org/whl/cu118
torch>=2.1.0
torchvision
torchaudio

openai-whisper
more-itertools
ffmpeg-python
gradio<=3.23.0
music-tag
voicefixer
psutil
phonemizer
pydantic==1.10.11
websockets
beartype==0.15.0
pykakasi
updated colab notebook 2023-10-24 23:39:46 +07:00			`--extra-index-url https://download.pytorch.org/whl/cu118`
			`torch>=2.1.0`
			`torchvision`
			`torchaudio`
added api_name for generation, added whisperx backend, relocated use whispercpp option to whisper backend list 2023-03-06 05:21:33 +07:00
updated colab notebook 2023-10-24 23:39:46 +07:00			`openai-whisper`
added preparation of LJSpeech-esque dataset 2023-02-17 05:42:55 +07:00			`more-itertools`
			`ffmpeg-python`
freeze gradio because I forgot to do it last week when it broke 2023-05-18 14:45:49 +07:00			`gradio<=3.23.0`
Initial refractor 2023-02-17 00:08:27 +07:00			`music-tag`
added preparation of LJSpeech-esque dataset 2023-02-17 05:42:55 +07:00			`voicefixer`
setup bnb on windows as needed 2023-03-16 20:48:48 +07:00			`psutil`
Freeze pydantic package to 1.10.11 inflect in DLAS requirements.txt installs pydantic 2.0.2, causing issues with the Gradio Webpage 2023-07-09 02:36:23 +07:00			`phonemizer`
made initialization faster if there's a lot of voice files (because glob fucking sucks), commiting changes buried on my training rig 2023-08-21 03:31:49 +07:00			`pydantic==1.10.11`
freeze beartype==0.15.0, unfrozen comes from x-clip in dlas 2023-09-19 00:18:44 +07:00			`websockets`
fixed setup scripts and Dockerfile to NOT use extra-index-url and instead use index-url (how this happened I don't know, since pytorch instructions use index-url), '''fixed''' phonemizing japanese for VALL-E with pykakasi 2023-10-12 00:27:46 +07:00			`beartype==0.15.0`
			`pykakasi`