bkraad47 / fat_llamaLinks
fat_llama is a Python package for upscaling audio files to FLAC or WAV formats using advanced audio processing techniques. It utilizes CUDA-accelerated calculations to enhance audio quality by upsampling and adding missing frequencies through FFT, resulting in richer and more detailed audio.
☆22Updated last year
Alternatives and similar repositories for fat_llama
Users that are interested in fat_llama are comparing it to the libraries listed below
Sorting:
- Apollo audio restoration Colab fork☆31Updated 10 months ago
- An official repository of "Music De-limiter Networks via Sample-wise Gain Inversion", which will be presented in WASPAA 2023.☆86Updated last year
- SOTA Piano Transformer model trained on 4.2GB of Solo Piano MIDI music☆25Updated 2 years ago
- ☆18Updated last year
- This is a dataset that aligns piano music MIDI with their corresponding textual descriptions and comments. It can be used for multi-modal…☆12Updated last year
- General Purpose Audio Effect Removal☆107Updated 2 years ago
- Latent Space Sound Design Tool based on the VAE of stable-audio-open☆15Updated last year
- High-speed batch audio enhancer that restores high-frequency details like Sony DSEE HX, converting any audio file to Hi-Res.☆25Updated 2 months ago
- Model for CDX23 (Cinematic Sound Demixing) contest☆45Updated last year
- GUI for Music-Source-Separation-Training☆20Updated 2 months ago
- MT3：多任务多音轨音乐转录的 Gradio 演示。（全中文汉化）☆12Updated 7 months ago
- Here we will track the latest Audio AI Agent, including speech, music, sound effects, etc.☆16Updated last year
- ☆61Updated 9 months ago
- Thesia is a Multi-track Spectrogram / Waveform viewer☆15Updated this week
- FxNorm-Automix - Implementation of automatic music mixing systems. We show how we can use wet music data and repurpose it to train a full…☆127Updated last year
- C++17 port of Demucs v3 (hybrid) and v4 (hybrid transformer) models with ggml and Eigen3☆147Updated 11 months ago
- Audio bandwidth enhancement with DNNs, addressing filter overfitting☆41Updated 2 years ago
- KUIELAB-MDX-Net got the 2nd place on the Leaderboard A and the 3rd place on the Leaderboard B in the MDX-Challenge ISMIR 2021☆25Updated 2 years ago
- Official repository for Aria-MIDI: a MIDI dataset of 1,186,253 transcribed solo-piano recordings.☆64Updated 4 months ago
- Full-attention multi-instrumental music transformer featuring asymmetrical encoding with octo-velocity, and chords counters tokens, optim…☆47Updated last year
- ☆53Updated last year
- Audio-to-Audio Schrodinger Bridges is a diffusion-based audio restoration model for bandwidth extension and inpainting.☆114Updated 2 months ago
- ☆51Updated last year
- A large-scale dataset of caption-annotated MIDI files.☆75Updated last year
- TU Darmstadt - Deep Learning: Architectures & Methods Project SS21☆36Updated 10 months ago
- [DEPRECIATED] [PyTorch 2.0] [638M] [85.33% acc] Full-attention multi-instrumental music transformer for supervised music generation, opti…☆32Updated last year
- 🎚️ Simple Matchering 2.0 Command Line Application☆91Updated last year
- [AAAI'24] Official dataset & demo code for MID-FiLD: MIDI Dataset for Fine-Level Dynamics☆18Updated last year
- Ravetable synthesis - Latent signal processing☆28Updated last month
- [SOTA] [92% acc] 786M-8k-44L-32H multi-instrumental music transformer with true full MIDI instruments range, efficient encoding, octo-vel…☆86Updated 10 months ago