{"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/nix-tts-an-incredibly-lightweight-end-to-end","title":"Nix-TTS: Lightweight and End-to-End Text-to-Speech via Module-wise Distillation","arxiv_id":"2203.15643","date":"2022-03-29","proceeding":null,"authors":["Rendi Chevi","Radityo Eko Prasojo","Alham Fikri Aji","Andros Tjandra","Sakriani Sakti"],"abstract":"Several solutions for lightweight TTS have shown promising results. Still, they either rely on a hand-crafted design that reaches non-optimum size or use a neural architecture search but often suffer training costs. We present Nix-TTS, a lightweight TTS achieved via knowledge distillation to a high-quality yet large-sized, non-autoregressive, and end-to-end (vocoder-free) TTS teacher model. Specifically, we offer module-wise distillation, enabling flexible and independent distillation to the encoder and decoder module. The resulting Nix-TTS inherited the advantageous properties of being non-autoregressive and end-to-end from the teacher, yet significantly smaller in size, with only 5.23M parameters or up to 89.34% reduction of the teacher model; it also achieves over 3.04x and 8.36x inference speedup on Intel-i7 CPU and Raspberry Pi 3B respectively and still retains a fair voice naturalness and intelligibility compared to the teacher model. We provide pretrained models and audio samples of Nix-TTS.","url_abs":"https://arxiv.org/abs/2203.15643v2","url_pdf":"https://arxiv.org/pdf/2203.15643v2.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":"nix-tts-an-incredibly-lightweight-end-to-end","repo_url":"https://github.com/rendchevi/nix-tts","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":null,"task_name":"CPU"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"task_slug":"text-to-speech","task_name":"Text to Speech"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"},{"method_slug":"non","method_name":"NON"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}