{"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":"/code/make-batch-for-text-to-audio","entry":"make_batch_for_text_to_audio","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-25T09:33:49+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":5,"n_papers_ran":5,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":1,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"unverified":0},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2407.02869","paper":"/paper/picoaudio-enabling-precise-timestamp-and","title":"PicoAudio: Enabling Precise Timestamp and Frequency Controllability of Audio Events in Text-to-audio Generation","date":null,"month_inferred_from_arxiv_id":"2024-07","title_source":"archive","repo":"picoaudio/picoaudio","path":"picoaudio/audioldm/pipeline.py","file_url":"https://github.com/picoaudio/picoaudio/blob/HEAD/picoaudio/audioldm/pipeline.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"409a71c470a245cd","mcp_get_code":{"code_sha256":"409a71c470a245cd"}},{"arxiv_id":"2406.04673","paper":"/paper/melfusion-synthesizing-music-from-image-and","title":"MeLFusion: Synthesizing Music from Image and Language Cues using Diffusion Models","date":"2024-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"schowdhury671/melfusion","path":"audioldm/pipeline.py","file_url":"https://github.com/schowdhury671/melfusion/blob/HEAD/audioldm/pipeline.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"409a71c470a245cd","mcp_get_code":{"code_sha256":"409a71c470a245cd"}},{"arxiv_id":"2406.04350","paper":"/paper/prompt-guided-precise-audio-editing-with","title":"Prompt-guided Precise Audio Editing with Diffusion Models","date":"2024-05-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"haoheliu/audioldm","path":"audioldm/pipeline.py","file_url":"https://github.com/haoheliu/audioldm/blob/HEAD/audioldm/pipeline.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"409a71c470a245cd","mcp_get_code":{"code_sha256":"409a71c470a245cd"}},{"arxiv_id":"2404.14381","paper":"/paper/tavgbench-benchmarking-text-to-audible-video","title":"TAVGBench: Benchmarking Text to Audible-Video Generation","date":"2024-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opennlplab/tavgbench","path":"audioldm/pipeline.py","file_url":"https://github.com/opennlplab/tavgbench/blob/HEAD/audioldm/pipeline.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"409a71c470a245cd","mcp_get_code":{"code_sha256":"409a71c470a245cd"}},{"arxiv_id":"2309.10740","paper":"/paper/accelerating-diffusion-based-text-to-audio","title":"ConsistencyTTA: Accelerating Diffusion-Based Text-to-Audio Generation with Consistency Distillation","date":"2023-09-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Bai-YT/ConsistencyTTA","path":"audioldm/pipeline.py","file_url":"https://github.com/Bai-YT/ConsistencyTTA/blob/HEAD/audioldm/pipeline.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"409a71c470a245cd","mcp_get_code":{"code_sha256":"409a71c470a245cd"}}]}