{"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/wenetspeech4tts-a-12800-hour-mandarin-tts","title":"WenetSpeech4TTS: A 12,800-hour Mandarin TTS Corpus for Large Speech Generation Model Benchmark","arxiv_id":"2406.05763","date":"2024-06-09","proceeding":null,"authors":["Linhan Ma","Dake Guo","Kun Song","Yuepeng Jiang","Shuai Wang","Liumeng Xue","Weiming Xu","Huan Zhao","BinBin Zhang","Lei Xie"],"abstract":"With the development of large text-to-speech (TTS) models and scale-up of the training data, state-of-the-art TTS systems have achieved impressive performance. In this paper, we present WenetSpeech4TTS, a multi-domain Mandarin corpus derived from the open-sourced WenetSpeech dataset. Tailored for the text-to-speech tasks, we refined WenetSpeech by adjusting segment boundaries, enhancing the audio quality, and eliminating speaker mixing within each segment. Following a more accurate transcription process and quality-based data filtering process, the obtained WenetSpeech4TTS corpus contains $12,800$ hours of paired audio-text data. Furthermore, we have created subsets of varying sizes, categorized by segment quality scores to allow for TTS model training and fine-tuning. VALL-E and NaturalSpeech 2 systems are trained and fine-tuned on these subsets to validate the usability of WenetSpeech4TTS, establishing baselines on benchmark for fair comparison of TTS systems. The corpus and corresponding benchmarks are publicly available on huggingface.","url_abs":"https://arxiv.org/abs/2406.05763v3","url_pdf":"https://arxiv.org/pdf/2406.05763v3.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":"wenetspeech4tts-a-12800-hour-mandarin-tts","repo_url":"https://github.com/dukGuo/valle-audiodec","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"text-to-speech","task_name":"Text to Speech"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2406.05763","atlas_url":"https://app.syntology.ai/?focus=2406.05763","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.05763"}},"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/dukGuo/valle-audiodec","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":3,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":4,"samples":[{"code_sha256_prefix":"81552a18b1a00e47","entry":"get_activation","repo":"dukGuo/valle-audiodec","repo_kind":"official","path":"AudioDec/layers/activation_function.py","file_url":"https://github.com/dukGuo/valle-audiodec/blob/HEAD/AudioDec/layers/activation_function.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"81552a18b1a00e47"}},{"code_sha256_prefix":"3a553ea2612332be","entry":"int2tuple","repo":"dukGuo/valle-audiodec","repo_kind":"official","path":"AudioDec/layers/conv_layer.py","file_url":"https://github.com/dukGuo/valle-audiodec/blob/HEAD/AudioDec/layers/conv_layer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"3a553ea2612332be"}},{"code_sha256_prefix":"0123af9b1d35f115","entry":"load_config","repo":"dukGuo/valle-audiodec","repo_kind":"official","path":"AudioDec/bin/utils.py","file_url":"https://github.com/dukGuo/valle-audiodec/blob/HEAD/AudioDec/bin/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"0123af9b1d35f115"}},{"code_sha256_prefix":"b7d9653fc51614dc","entry":"stft","repo":"dukGuo/valle-audiodec","repo_kind":"official","path":"AudioDec/losses/stft_loss.py","file_url":"https://github.com/dukGuo/valle-audiodec/blob/HEAD/AudioDec/losses/stft_loss.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"b7d9653fc51614dc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}