AI & ML interests
None defined yet.
Recent Activity
Ace Step
MuScriptor
Transcribe audio files into MIDI with optional instrument filtering
Diffrhythm2
Generate music from lyrics and style prompts
UDREAM
Removes room reverb from a speech recording
Audio Inpainting Diffusion
Fill missing parts in an audio clip using diffusion model
Beat This
Detect beats and downbeats in audio
HTS AT
Lightweight audio classification/sound event detection model
Open-Unmix
Separate music into vocals, drums, bass, and other stems
FST AI Music Detection
Detect AI GenMusic via a Fusion Segment Transformer
TTS Tacotron2 LJSpeech
Generate spoken audio from text
Bark
Generate realistic speech and sounds from text
STAGE
Bass/Drums Accompaniment Generation
VoiceFixer
Restore degraded speech audio with VoiceFixer
Banquet
Separate any instrument from a mix using an audio query
MusiConGen
Text-to-music generation with chord and rhythm control
Woosh-DFlow (Text-to-Audio SFX)
Generate a short sound effect from text
Melodyflow
Generate music from text and optional melody
Improvnet
Convert piano MIDI to jazz or classical style
BABE-2
Diffusion-based restoration for historical recordings
FxNorm Automix
Automatic Mixing Model based on Fx-Normalization
UNISON
Unified Model For SpeechGen, SoundGen, and In-Scene-Editing
MEGAMI
Automatic Mixing via Generative Model of Effect Embeddings