{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/msanii-high-fidelity-music-synthesis-on-a","title":"Msanii: High Fidelity Music Synthesis on a Shoestring Budget","arxiv_id":"2301.06468","date":"2023-01-16","proceeding":null,"authors":["Kinyugo Maina"],"abstract":"In this paper, we present Msanii, a novel diffusion-based model for synthesizing long-context, high-fidelity music efficiently. Our model combines the expressiveness of mel spectrograms, the generative capabilities of diffusion models, and the vocoding capabilities of neural vocoders. We demonstrate the effectiveness of Msanii by synthesizing tens of seconds (190 seconds) of stereo music at high sample rates (44.1 kHz) without the use of concatenative synthesis, cascading architectures, or compression techniques. To the best of our knowledge, this is the first work to successfully employ a diffusion-based model for synthesizing such long music samples at high sample rates. Our demo can be found https://kinyugo.github.io/msanii-demo and our code https://github.com/Kinyugo/msanii .","url_abs":"https://arxiv.org/abs/2301.06468v1","url_pdf":"https://arxiv.org/pdf/2301.06468v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"msanii-high-fidelity-music-synthesis-on-a","repo_url":"https://github.com/kinyugo/msanii","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"audio-inpainting","task_name":"Audio inpainting"},{"task_slug":"music-generation","task_name":"Music Generation"},{"task_slug":"music-style-transfer","task_name":"Music Style Transfer"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2301.06468","atlas_url":"https://app.syntology.ai/?focus=2301.06468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.06468"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kinyugo/msanii","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5,"unverified":1},"by_repo_kind":{"official":{"samples":6,"ran":5,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"959bae2750dbabbf","entry":"Downsample","repo":"kinyugo/msanii","repo_kind":"official","path":"msanii/modules/modules.py","file_url":"https://github.com/kinyugo/msanii/blob/HEAD/msanii/modules/modules.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"959bae2750dbabbf"}},{"code_sha256_prefix":"1fd7ab5b924af296","entry":"InputFn","repo":"kinyugo/msanii","repo_kind":"official","path":"msanii/modules/modules.py","file_url":"https://github.com/kinyugo/msanii/blob/HEAD/msanii/modules/modules.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1fd7ab5b924af296"}},{"code_sha256_prefix":"6c4e4f10a8576456","entry":"OutputFn","repo":"kinyugo/msanii","repo_kind":"official","path":"msanii/modules/modules.py","file_url":"https://github.com/kinyugo/msanii/blob/HEAD/msanii/modules/modules.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6c4e4f10a8576456"}},{"code_sha256_prefix":"6e3ea6105d69ee0c","entry":"get_import_path_from_instance","repo":"kinyugo/msanii","repo_kind":"official","path":"msanii/config/utils.py","file_url":"https://github.com/kinyugo/msanii/blob/HEAD/msanii/config/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6e3ea6105d69ee0c"}},{"code_sha256_prefix":"4260c3983f5576f7","entry":"import_from_path","repo":"kinyugo/msanii","repo_kind":"official","path":"msanii/config/utils.py","file_url":"https://github.com/kinyugo/msanii/blob/HEAD/msanii/config/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4260c3983f5576f7"}},{"code_sha256_prefix":"88cdbe7f473723aa","entry":"from_config","repo":"kinyugo/msanii","repo_kind":"official","path":"msanii/config/utils.py","file_url":"https://github.com/kinyugo/msanii/blob/HEAD/msanii/config/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"88cdbe7f473723aa"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}