{"id":13434515,"url":"https://github.com/pmlg/generative_music_playground","last_synced_at":"2025-03-17T14:31:33.168Z","repository":{"id":77536478,"uuid":"204440486","full_name":"pmlg/generative_music_playground","owner":"pmlg","description":"Links for music + machine learning","archived":false,"fork":false,"pushed_at":"2024-12-09T17:25:01.000Z","size":122,"stargazers_count":172,"open_issues_count":1,"forks_count":18,"subscribers_count":12,"default_branch":"master","last_synced_at":"2024-12-09T18:30:52.262Z","etag":null,"topics":["ai","generative","music"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/pmlg.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2019-08-26T09:20:03.000Z","updated_at":"2024-12-09T17:25:04.000Z","dependencies_parsed_at":"2023-12-14T09:29:59.466Z","dependency_job_id":"20bb7b29-4439-4bc2-8e12-1d2d755f4bfe","html_url":"https://github.com/pmlg/generative_music_playground","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pmlg%2Fgenerative_music_playground","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pmlg%2Fgenerative_music_playground/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pmlg%2Fgenerative_music_playground/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pmlg%2Fgenerative_music_playground/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/pmlg","download_url":"https://codeload.github.com/pmlg/generative_music_playground/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244050268,"owners_count":20389665,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","generative","music"],"created_at":"2024-07-31T02:01:59.487Z","updated_at":"2025-03-17T14:31:33.162Z","avatar_url":"https://github.com/pmlg.png","language":null,"funding_links":[],"categories":["Others"],"sub_categories":[],"readme":"# Generative Music Playground by Perth Machine Learning Group\n## Description\nLinks for music + machine learning. \nThis is a curated list of links for people who want to explore generating music with deep learning. \n\nCheck https://www.meetup.com/Perth-Machine-Learning-Group/events for updates on in-person meetups\n\n\nRecommended|   |   |   |   |   |   |\n---------------|---|---|---|---|---|---|\n**Name**                 |**Description**|**Demo**|**Code**|**Paper**|**Suitable for**|**Released**|\n[Foundation Models for Music: A Survey]([https://arxiv.org/abs/2408.14340])|Review paper on the state-of-the-art foundation models for music|||[Paper](https://arxiv.org/pdf/2408.14340)||August 2024|\n**Generating Audio(.wav or .mp3 files)**\n[**MusicFX (Google)**](https://aitestkitchen.withgoogle.com/tools/music-fx)|Generate music from text|[Blog](https://google-research.github.io/seanet/musiclm/musicfx/)\u003cbr\u003e\u003cbr\u003e[Audio](https://google-research.github.io/seanet/musiclm/examples/)\u003cbr\u003e\u003c/br\u003e[Youtube](https://www.youtube.com/watch?v=g6FRkAbZPQo)||[Paper](https://arxiv.org/abs/2301.11325)|Non-coders|December 2023|\n[**Stable Audio (Stability AI)**](https://stability.ai/stableaudio)|Generate music and sound effects from text.|||[Research Blog](https://stability.ai/research/stable-audio-efficient-timing-latent-diffusion)\u003cbr\u003e\u003cbr\u003e[Github](https://github.com/Stability-AI/stable-audio-tools)\u003cbr\u003e\u003cbr\u003e|Non-coders|September 2023|\n[**MusicGen (Meta AI)**](https://github.com/facebookresearch/audiocraft)|Generate music from text (controllable)|[Hugging Face Spaces](https://huggingface.co/spaces/facebook/MusicGen)\u003cbr\u003e\u003cbr\u003e[Audio](https://huggingface.co/papers/2306.05284)|[Google Colab](https://colab.research.google.com/drive/1-Xe9NCdIs2sCUbiSmwHXozK6AAhMm7_i?usp=sharing)|[Paper](https://arxiv.org/abs/2306.05284)|Non-coders|June 2023|\n[Make An Audio (ByteDance)](https://github.com/Text-to-Audio/Make-An-Audio)||[Github Pages](https://text-to-audio.github.io/)\u003cbr\u003e\u003cbr\u003e[Hugging Face Spaces](https://huggingface.co/spaces/AIGC-Audio/Make_An_Audio)|[Github](https://github.com/Text-to-Audio/Make-An-Audio)|[Paper](https://text-to-audio.github.io/paper.pdf)||June 2023|\n[Harmonai (Stability AI)](https://www.harmonai.org/)|Generate novel audio from pretrained models or fine-tune with your own audio tracks|[Hugging Face Spaces](https://huggingface.co/spaces/harmonai/dance-diffusion)\u003cbr /\u003e\u003cbr /\u003e[24/7 Youtube stream](https://www.youtube.com/watch?v=kJgxC9d0p50)|[Dance Diffusion](https://colab.research.google.com/github/Harmonai-org/sample-generator/blob/main/Dance_Diffusion.ipynb)\u003cbr /\u003e\u003cbr /\u003e[Fine-tuning Dance Diffusion](https://colab.research.google.com/github/Harmonai-org/sample-generator/blob/main/Finetune_Dance_Diffusion.ipynb)\u003cbr\u003e\u003c/br\u003e[Github](https://github.com/Harmonai-org/sample-generator)|[Guide](https://drive.google.com/file/d/1nEFEpK27v0nytNXmmYQb06X_RI6kKPve/view)\u003cbr /\u003e\u003cbr /\u003e[WandB article](https://wandb.ai/wandb_gen/audio/reports/A-Gentle-Introduction-to-Dance-Diffusion--VmlldzoyNjg1Mzky)|Non-coders (Hugging Face), coders (Google Colab)|Oct 2022|\n[Jukebox (OpenAI)](https://openai.com/blog/jukebox/)|Choose artist, genre, lyrics, and generate audio|[Audio](https://jukebox.openai.com/)|[Google Colab](https://colab.research.google.com/github/openai/jukebox/blob/master/jukebox/Interacting_with_Jukebox.ipynb)|[Paper](https://arxiv.org/abs/2005.00341)|Coders (Google Colab)|April 2020|\n**Generating MIDI(.mid files)**\n[**MuseNet (OpenAI)**](https://openai.com/blog/musenet)|Generate new melodies(MIDI file). Scroll down to \"Compose in the style of Chopin\", generate a continuation of that song, and download the MIDI |[Audio](https://soundcloud.com/openai_audio/sets/musenet)|||Non-coders|Apr 2019|\n[**Piano Transformer (Google)**](https://magenta.tensorflow.org/piano-transformer)|Generate piano MIDI notes from scratch or from a starting MIDI file|[Audio](https://magenta.tensorflow.org/assets/piano_transformer/clair_de_lune_continuation.mp3)|[Google Colab](https://colab.research.google.com/notebooks/magenta/piano_transformer/piano_transformer.ipynb)||Non-coders|Sep 2019|\n**Other resources**\n**MIDI(.mid files)**\n[Basic Pitch (Spotify)](https://basicpitch.spotify.com)|Audio-to-MIDI converter with pitch bend detection. Record with your device, or upload an audio file to obtain a MIDI transcription||||Non-coders|June 2022|\n[Magenta Studio (Google)](https://magenta.tensorflow.org/studio)|Compose multitrack melodies/chords in Ableton Live (music production software)||[Github](https://github.com/magenta/magenta-studio)||Ableton users, music producers|Feb 2019\n[MIDI DDSP (Google Magenta)](https://magenta.tensorflow.org/midi-ddsp)|MIDI-to-Audio synthesis (expression control)|[Github Pages](https://midi-ddsp.github.io/)\u003cbr\u003e\u003cbr\u003e[Blog](https://magenta.tensorflow.org/midi-ddsp)|[Github](https://github.com/magenta/midi-ddsp)|[Paper](https://openreview.net/pdf?id=UseMOjWENv)||Jan 2022|\n[Hello Magenta (Google)](https://colab.research.google.com/notebooks/magenta/hello_magenta/hello_magenta.ipynb)|Introduction to Google Magenta - includes MelodyRNN and MusicVAE||[Google Colab](https://colab.research.google.com/notebooks/magenta/hello_magenta/hello_magenta.ipynb)\u003cbr /\u003e\u003cbr /\u003e[Magenta.js](https://hello-magenta.glitch.me/)||Coders|\n[Music Autobot](https://musicautobot.com)|Generate MIDI - song generation, harmonization, generating melodies, and remixing existing songs.||||Non-coders,non-musicians|\n[FreeMIDI](https://freemidi.org/)|Download free MIDI files here||||Non-coders,non-musicians|\n[Online Sequencer](https://onlinesequencer.net/)|Make your own MIDI file from scratch||||Non-coders,non-musicians|\n**Audio(.wav or .mp3 files)**\n[DDSP-VST (Google Magenta)](https://magenta.tensorflow.org/ddsp-vst)|DDSP morphs audio into a range of different instruments.|[Blog](https://magenta.tensorflow.org/ddsp)\u003cbr\u003e\u003cbr\u003e[Page](https://magenta.tensorflow.org/ddsp-vst)|[Github](https://github.com/magenta/ddsp-vst)|[Paper](https://openreview.net/forum?id=B1x1ma4tDr)|Music producers|Jan 2020\n[Spleeter by Deezer](https://deezer.io/releasing-spleeter-deezer-r-d-source-separation-engine-2b88985e797e)|Music source separation library. Upload an audio file, isolate vocals or instrumental||[Github](https://github.com/deezer/spleeter)\u003cbr /\u003e\u003cbr /\u003e[Google Colab](https://colab.research.google.com/github/deezer/spleeter/blob/master/spleeter.ipynb)||Non-coders, coders|Nov 2019|\n[GANSynth](https://magenta.tensorflow.org/gansynth)|Upload a MIDI file,download an audio file of the interpolation between different instruments|[Audio](https://storage.googleapis.com/magentadata/papers/gansynth/index.html)|[Google Colab](https://colab.research.google.com/notebooks/magenta/gansynth/gansynth_demo.ipynb)|[Paper](https://openreview.net/forum?id=H1xQVn09FX)|Non-coders|Feb 2019|\n[MusicVAE (Google)](https://magenta.tensorflow.org/music-vae)|Generate audio, interpolate between 2 different melodies or drum beats |[Audio](https://magenta.tensorflow.org/assets/music_vae/mel_2bar-b2m.mp3)|[Google Colab](https://colab.research.google.com/notebooks/magenta/music_vae/music_vae.ipynb)|[Paper](https://arxiv.org/abs/1806.00195)|Non-coders|March 2018|\n**Introduction to Music**||||||\n[Chrome Music Lab](https://musiclab.chromeexperiments.com/Experiments)||||||\n[Learning Music with Ableton](https://learningmusic.ableton.com/)||||||\n[Learning Synths (Ableton)](https://learningsynths.ableton.com/)||||||\n[Music Theory](https://www.musictheory.net/lessons/)||||||\n**Miscellaneous**||||||\n[Lyria (Google DeepMind)](https://deepmind.google/discover/blog/transforming-the-future-of-music-creation/)|AI Music Generation model used in Youtube's Dream Track for Shorts and AI Music Tools|[Youtube Blog](https://blog.youtube/inside-youtube/ai-and-music-experiment/)\u003cbr\u003e\u003cbr\u003e[DeepMind Blog](https://deepmind.google/discover/blog/transforming-the-future-of-music-creation/)||||TBA \n[Microsoft - Muzic](https://github.com/microsoft/muzic)|Research project on AI music that empowers music understanding and generation with deep learning and artificial intelligence||[Github](https://github.com/microsoft/muzic)\u003cbr\u003e\u003cbr\u003e[Github Pages](https://ai-muzic.github.io/)|||\n[NVIDIA - Maxine Audio Effects SDK](https://github.com/NVIDIA/MAXINE-AFX-SDK)|API Source Code and Sample Applications. Various audio effects for broadcast use cases with real-time audio processing||[Github](https://github.com/NVIDIA/MAXINE-AFX-SDK)\u003cbr\u003e\u003cbr\u003e[NVIDIA Broadcast SDK](https://www.nvidia.com/en-au/geforce/broadcasting/broadcast-sdk/resources/)\u003cbr\u003e\u003cbr\u003e[NVIDIA NGC](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/maxine/collections/maxine)|||\n[Google Magenta](https://magenta.tensorflow.org/)|Open source research project exploring the role of machine learning as a tool in the creative process|[Blog](https://magenta.tensorflow.org/blog)\u003cbr\u003e\u003cbr\u003e[Talks](https://magenta.tensorflow.org/talks)\u003cbr\u003e\u003cbr\u003e[Research](https://magenta.tensorflow.org/research)|[Github](https://github.com/magenta)\u003cbr\u003e\u003cbr\u003e[Magenta Github](https://github.com/magenta/magenta)|||\n[PapersWithCode - Music Generation](https://paperswithcode.com/task/music-generation)|Papers, code, evaluation papers, datasets|||||\n[PapersWithCode - Music Source Separation](https://paperswithcode.com/task/music-source-separation)|Papers, code, evaluation papers, datasets|||||\n[Python In Music](https://wiki.python.org/moin/PythonInMusic)|List of music software written in Python,music software supporting Python,music programming in Python, etc.|||||\n[Github - Deep Learning for Music Generation by Carlos Hernández-Oliván](https://github.com/carlosholivan/DeepLearningMusicGeneration)|List of articles related to deep learning applied to music generation|||||\n[Github - Deep Learning papers in music by Yann Bayle](https://github.com/ybayle/awesome-deep-learning-music)|List of articles related to deep learning applied to music|||||\n[Github - Audio Development Tools by Yuan Man](https://github.com/Yuan-ManX/audio-development-tools)|List of sound, audio and music development tools||||\n[TorchAudio](https://pytorch.org/audio/stable/index.html)|Library for audio and signal processing with PyTorch|||||\n[Deep Learning with audio thread - Fast.AI forum](https://forums.fast.ai/t/deep-learning-with-audio-thread/38123)|List of links related to deep learning applied to audio|||||\n[International Society for Music Information Retrieval(ISMIR)](https://www.ismir.net/resources/)|Links to datasets, educational material, tutorials, software related to music information retrieval|||||\n[NLP4MusA Youtube channel](https://www.youtube.com/channel/UCtWGAGz6I_1aRetS8U4rYcA)|Natural Language Processing for Music and Audio - Zoom talks by NLP+music researchers|||||\n[SigSep](https://sigsep.github.io/literature/)|Open resources for music source separation. Datasets, code, literature, tutorials||[Github](https://github.com/sigsep/open-unmix-pytorch)|||\n[Google Experiments - Music](https://experiments.withgoogle.com/search?q=music)||||||\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpmlg%2Fgenerative_music_playground","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpmlg%2Fgenerative_music_playground","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpmlg%2Fgenerative_music_playground/lists"}