{"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/plot-spectrogram-to-numpy","entry":"plot_spectrogram_to_numpy","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":8,"n_papers_ran":0,"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":5,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":10,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":5},"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":"2402.12208","paper":"/paper/language-codec-reducing-the-gaps-between","title":"Language-Codec: Bridging Discrete Codec Representations and Speech Language Models","date":"2024-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jishengpeng/languagecodec","path":"languagecodec_decoder/helpers.py","file_url":"https://github.com/jishengpeng/languagecodec/blob/HEAD/languagecodec_decoder/helpers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e9b4eebcade00ef9","mcp_get_code":{"code_sha256":"e9b4eebcade00ef9"}},{"arxiv_id":"2306.00814","paper":"/paper/vocos-closing-the-gap-between-time-domain-and","title":"Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis","date":"2023-06-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gemelo-ai/vocos","path":"vocos/helpers.py","file_url":"https://github.com/gemelo-ai/vocos/blob/HEAD/vocos/helpers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e9b4eebcade00ef9","mcp_get_code":{"code_sha256":"e9b4eebcade00ef9"}},{"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/utils.py","file_url":"https://github.com/vinairesearch/xphonebert/blob/HEAD/VITS_with_XPhoneBERT/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d1de5b72a4f78810","mcp_get_code":{"code_sha256":"d1de5b72a4f78810"}},{"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":"jaywalnut310/vits","path":"utils.py","file_url":"https://github.com/jaywalnut310/vits/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d1de5b72a4f78810","mcp_get_code":{"code_sha256":"d1de5b72a4f78810"}},{"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":"NVIDIA/tacotron2","path":"plotting_utils.py","file_url":"https://github.com/NVIDIA/tacotron2/blob/HEAD/plotting_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"2545971684f8134d","mcp_get_code":{"code_sha256":"2545971684f8134d"}},{"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":"jaywalnut310/glow-tts","path":"utils.py","file_url":"https://github.com/jaywalnut310/glow-tts/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9dc202f235585e84","mcp_get_code":{"code_sha256":"9dc202f235585e84"}},{"arxiv_id":"2105.06337","paper":"/paper/grad-tts-a-diffusion-probabilistic-model-for","title":"Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech","date":"2021-05-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"WelkinYang/GradTTS","path":"utils.py","file_url":"https://github.com/WelkinYang/GradTTS/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9dc202f235585e84","mcp_get_code":{"code_sha256":"9dc202f235585e84"}},{"arxiv_id":"2005.11129","paper":"/paper/glow-tts-a-generative-flow-for-text-to-speech","title":"Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search","date":"2020-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ankurdhuriya/multispeaker-glow-tts","path":"utils.py","file_url":"https://github.com/ankurdhuriya/multispeaker-glow-tts/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9dc202f235585e84","mcp_get_code":{"code_sha256":"9dc202f235585e84"}},{"arxiv_id":"1907.04448","paper":"/paper/learning-to-speak-fluently-in-a-foreign","title":"Learning to Speak Fluently in a Foreign Language: Multilingual Speech Synthesis and Cross-Language Voice Cloning","date":"2019-07-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Jeevesh8/Cross-Lingual-Voice-Cloning","path":"plotting_utils.py","file_url":"https://github.com/Jeevesh8/Cross-Lingual-Voice-Cloning/blob/HEAD/plotting_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":false,"code_sha256_prefix":"2545971684f8134d","mcp_get_code":{"code_sha256":"2545971684f8134d"}},{"arxiv_id":"1905.11286","paper":"/paper/stochastic-gradient-methods-with-layer-wise","title":"Stochastic Gradient Methods with Layer-wise Adaptive Moments for Training of Deep Networks","date":"2019-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Edresson/VoiceSplit","path":"utils/tensorboard.py","file_url":"https://github.com/Edresson/VoiceSplit/blob/HEAD/utils/tensorboard.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":"c34124e879d7f774","mcp_get_code":{"code_sha256":"c34124e879d7f774"}}]}