{"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/convert-pad-shape","entry":"convert_pad_shape","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+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":15,"n_papers_ran":12,"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":4,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":15,"n_places_pointer_only":4,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":3},"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":"2504.00858","paper":"/paper/whispering-under-the-eaves-protecting-user","title":"Whispering Under the Eaves: Protecting User Privacy Against Commercial and LLM-powered Automatic Speech Recognition Systems","date":"2025-04-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"WeifeiJin/AudioShield","path":"commons.py","file_url":"https://github.com/WeifeiJin/AudioShield/blob/HEAD/commons.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"59ae0708b1e8d94b","mcp_get_code":{"code_sha256":"59ae0708b1e8d94b"}},{"arxiv_id":"2410.20742","paper":"/paper/mitigating-unauthorized-speech-synthesis-for","title":"Mitigating Unauthorized Speech Synthesis for Voice Protection","date":"2024-10-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wxzyd123/pivotal_objective_perturbation","path":"vits/commons.py","file_url":"https://github.com/wxzyd123/pivotal_objective_perturbation/blob/HEAD/vits/commons.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"59ae0708b1e8d94b","mcp_get_code":{"code_sha256":"59ae0708b1e8d94b"}},{"arxiv_id":"2408.15297","paper":"/paper/yolo-stutter-end-to-end-region-wise-speech","title":"YOLO-Stutter: End-to-end Region-Wise Speech Dysfluency Detection","date":"2024-08-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rorizzz/yolo-stutter","path":"yolo-stutter/utils/vits/commons.py","file_url":"https://github.com/rorizzz/yolo-stutter/blob/HEAD/yolo-stutter/utils/vits/commons.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"59ae0708b1e8d94b","mcp_get_code":{"code_sha256":"59ae0708b1e8d94b"}},{"arxiv_id":"2312.01479","paper":"/paper/openvoice-versatile-instant-voice-cloning","title":"OpenVoice: Versatile Instant Voice Cloning","date":"2023-12-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"myshell-ai/openvoice","path":"openvoice/commons.py","file_url":"https://github.com/myshell-ai/openvoice/blob/HEAD/openvoice/commons.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"feec90b898e6e43b","mcp_get_code":{"code_sha256":"feec90b898e6e43b"}},{"arxiv_id":"2311.04693","paper":"/paper/diff-hiervc-diffusion-based-hierarchical","title":"Diff-HierVC: Diffusion-based Hierarchical Voice Conversion with Robust Pitch Generation and Masked Prior for Zero-shot Speaker Adaptation","date":"2023-11-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hayeong0/Diff-HierVC","path":"module/commons.py","file_url":"https://github.com/hayeong0/Diff-HierVC/blob/HEAD/module/commons.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"59ae0708b1e8d94b","mcp_get_code":{"code_sha256":"59ae0708b1e8d94b"}},{"arxiv_id":"2310.01889","paper":"/paper/ring-attention-with-blockwise-transformers","title":"Ring Attention with Blockwise Transformers for Near-Infinite Context","date":"2023-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"seongho608/ringformer","path":"commons.py","file_url":"https://github.com/seongho608/ringformer/blob/HEAD/commons.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"59ae0708b1e8d94b","mcp_get_code":{"code_sha256":"59ae0708b1e8d94b"}},{"arxiv_id":"2305.19709","paper":"/paper/xphonebert-a-pre-trained-multilingual-model","title":"XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speech","date":"2023-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vinairesearch/xphonebert","path":"VITS_with_XPhoneBERT/commons.py","file_url":"https://github.com/vinairesearch/xphonebert/blob/HEAD/VITS_with_XPhoneBERT/commons.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"59ae0708b1e8d94b","mcp_get_code":{"code_sha256":"59ae0708b1e8d94b"}},{"arxiv_id":"2305.06908","paper":"/paper/comospeech-one-step-speech-and-singing-voice","title":"CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency Model","date":"2023-05-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhenye234/CoMoSpeech","path":"model/utils.py","file_url":"https://github.com/zhenye234/CoMoSpeech/blob/HEAD/model/utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"59ae0708b1e8d94b","mcp_get_code":{"code_sha256":"59ae0708b1e8d94b"}},{"arxiv_id":"2210.06370","paper":"/paper/can-we-use-common-voice-to-train-a-multi","title":"Can we use Common Voice to train a Multi-Speaker TTS system?","date":"2022-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ogunlao/glowtts_stdp","path":"modules/glow_tts_modules/glow_tts_submodules.py","file_url":"https://github.com/ogunlao/glowtts_stdp/blob/HEAD/modules/glow_tts_modules/glow_tts_submodules.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d2803ec5ec6424b4","mcp_get_code":{"code_sha256":"d2803ec5ec6424b4"}},{"arxiv_id":"2206.04658","paper":"/paper/bigvgan-a-universal-neural-vocoder-with-large","title":"BigVGAN: A Universal Neural Vocoder with Large-Scale Training","date":"2022-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sh-lee-prml/BigVGAN","path":"commons.py","file_url":"https://github.com/sh-lee-prml/BigVGAN/blob/HEAD/commons.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"59ae0708b1e8d94b","mcp_get_code":{"code_sha256":"59ae0708b1e8d94b"}},{"arxiv_id":"2204.11792","paper":"/paper/syntaspeech-syntax-aware-generative","title":"SyntaSpeech: Syntax-Aware Generative Adversarial Text-to-Speech","date":null,"month_inferred_from_arxiv_id":"2022-04","title_source":"archive","repo":"yerfor/syntaspeech","path":"modules/commons/rel_transformer.py","file_url":"https://github.com/yerfor/syntaspeech/blob/HEAD/modules/commons/rel_transformer.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"59ae0708b1e8d94b","mcp_get_code":{"code_sha256":"59ae0708b1e8d94b"}},{"arxiv_id":"2109.15166","paper":"/paper/portaspeech-portable-and-high-quality","title":"PortaSpeech: Portable and High-Quality Generative Text-to-Speech","date":"2021-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"keonlee9420/PortaSpeech","path":"model/blocks.py","file_url":"https://github.com/keonlee9420/PortaSpeech/blob/HEAD/model/blocks.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"59ae0708b1e8d94b","mcp_get_code":{"code_sha256":"59ae0708b1e8d94b"}},{"arxiv_id":"2109.13821","paper":"/paper/diffusion-based-voice-conversion-with-fast","title":"Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme","date":"2021-09-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"trinhtuanvubk/diff-vc","path":"model/utils.py","file_url":"https://github.com/trinhtuanvubk/diff-vc/blob/HEAD/model/utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"59ae0708b1e8d94b","mcp_get_code":{"code_sha256":"59ae0708b1e8d94b"}},{"arxiv_id":"2106.06103","paper":"/paper/conditional-variational-autoencoder-with","title":"Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech","date":null,"month_inferred_from_arxiv_id":"2021-06","title_source":"archive","repo":"isletennos/mmvc_trainer","path":"models.py","file_url":"https://github.com/isletennos/mmvc_trainer/blob/HEAD/models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"59ae0708b1e8d94b","mcp_get_code":{"code_sha256":"59ae0708b1e8d94b"}},{"arxiv_id":"2006.04558","paper":"/paper/fastspeech-2-fast-and-high-quality-end-to-end","title":"FastSpeech 2: Fast and High-Quality End-to-End Text to Speech","date":"2020-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shivammehta25/BetterFastSpeech2","path":"fs2/utils/model.py","file_url":"https://github.com/shivammehta25/BetterFastSpeech2/blob/HEAD/fs2/utils/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ecfa879e1ca09709","mcp_get_code":{"code_sha256":"ecfa879e1ca09709"}}]}