{"id":182860,"date":"2024-02-16T21:24:17","date_gmt":"2024-02-17T03:24:17","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2024\/02\/base-tts-audio-samples"},"modified":"2024-02-16T21:24:17","modified_gmt":"2024-02-17T03:24:17","slug":"base-tts-audio-samples","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2024\/02\/base-tts-audio-samples","title":{"rendered":"BASE TTS: Audio samples"},"content":{"rendered":"<p><a class=\"aligncenter blog-photo\" href=\"https:\/\/lifeboat.com\/blog.images\/base-tts-audio-samples2.jpg\"><\/a><\/p>\n<p>Audio samples for the paper \u201c<a class=\"\" href=\"https:\/\/www.amazon.science\/publications\/base-tts-lessons-from-building-a-billion-parameter-text-to-speech-model-on-100k-hours-of-data\" data-cms-ai=\"0\" >BASE TTS: Lessons from building a billion-parameter text-to-speech model on 100K hours of data<\/a>\u201d<\/p>\n<p>Abstract: We introduce a text-to-speech (TTS) model called BASE TTS, which stands for Big Adaptive Streamable TTS with Emergent abilities. BASE TTS is the largest TTS model to-date, trained on 100K hours of public domain speech data, achieving a new state-of-the-art in speech naturalness. It deploys a 1-billion-parameter autoregressive Transformer that converts raw texts into discrete codes (\u201cspeechcodes\u201d) followed by a convolution-based decoder which converts these speechcodes into waveforms in an incremental, streamable manner. Further, our speechcodes are built using a novel speech tokenization technique that features speaker ID disentanglement and compression with byte-pair encoding. Echoing the widely-reported \u201cemergent abilities\u201d of large language models when trained on increasing volume of data, we show that BASE TTS variants built with 10K+ hours and 500M+ parameters begin to demonstrate natural prosody on textually complex sentences.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Audio samples for the paper \u201cBASE TTS: Lessons from building a billion-parameter text-to-speech model on 100K hours of data\u201d Abstract: We introduce a text-to-speech (TTS) model called BASE TTS, which stands for Big Adaptive Streamable TTS with Emergent abilities. BASE TTS is the largest TTS model to-date, trained on 100K hours of public domain speech [\u2026]<\/p>\n","protected":false},"author":359,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[15],"tags":[],"class_list":["post-182860","post","type-post","status-publish","format-standard","hentry","category-habitats"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/182860","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/users\/359"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=182860"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/182860\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=182860"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=182860"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=182860"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}