Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.
inpaint-anything
interactive-tracking
segment-anything
track-anything
video-object-segmentation
video-object-tracking
Updated 2025-12-13 12:02:33 +01:00
ModelScope: bring the notion of Model-as-a-Service to life.
Updated 2025-12-10 04:34:35 +01:00
Updated 2025-12-09 10:58:41 +01:00
ECCV2022 - Real-Time Intermediate Flow Estimation for Video Frame Interpolation
Updated 2025-09-10 08:32:03 +02:00
Instant voice cloning by MIT and MyShell. Audio foundation model.
Updated 2025-04-19 17:59:59 +02:00
A Python/Pytorch app for easily synthesising human voices
Updated 2024-12-02 04:42:25 +01:00
Easily train a good VC model with voice data <= 10 mins!
audio-analysis
change
conversational-ai
conversion
converter
retrieval-model
retrieve-data
rvc
so-vits-svc
sovits
vc
vits
voice
voice-conversion
voice-converter
voiceconversion
Updated 2024-11-24 16:09:44 +01:00
Official implementation of AnimateDiff.
Updated 2024-07-17 10:19:47 +02:00
an improved version of Real-time-voice-cloning
Updated 2024-03-06 13:35:47 +01:00
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
deep-learning
glow-tts
hifigan
melgan
multi-speaker-tts
python
pytorch
speaker-encoder
speaker-encodings
speech
speech-synthesis
tacotron
text-to-speech
tts
tts-model
vocoder
voice-cloning
voice-conversion
voice-synthesis
Updated 2024-02-10 15:20:58 +01:00
*CREPE+HYBRID TRAINING* A very experimental fork of the Retrieval-based-Voice-Conversion-WebUI repo that incorporates a variety of other f0 methods, along with a hybrid f0 nanmedian method.
Updated 2023-08-22 01:44:32 +02:00