From 3b21a9501b1a6eb7e663fc86a88854833fb3758e Mon Sep 17 00:00:00 2001 From: jinzr Date: Mon, 5 Feb 2024 12:41:19 +0800 Subject: [PATCH] init commit --- egs/ljspeech/TTS/README.md | 16 ++++++++++++++++ egs/vctk/TTS/README.md | 14 ++++++++++++++ 2 files changed, 30 insertions(+) create mode 100644 egs/ljspeech/TTS/README.md create mode 100644 egs/vctk/TTS/README.md diff --git a/egs/ljspeech/TTS/README.md b/egs/ljspeech/TTS/README.md new file mode 100644 index 0000000000..d3c7348623 --- /dev/null +++ b/egs/ljspeech/TTS/README.md @@ -0,0 +1,16 @@ +# Introduction + +This is a public domain speech dataset consisting of 13,100 short audio clips of a single speaker reading passages from 7 non-fiction books. +A transcription is provided for each clip. +Clips vary in length from 1 to 10 seconds and have a total length of approximately 24 hours. + +The texts were published between 1884 and 1964, and are in the public domain. +The audio was recorded in 2016-17 by the [LibriVox](https://librivox.org/) project and is also in the public domain. + +The above information is from the [LJSpeech website](https://keithito.com/LJ-Speech-Dataset/). + +# VITS + +This recipe provides a VITS model trained on the LJSpeech dataset. + +Pretrained model can be found [here](https://huggingface.co/Zengwei/icefall-tts-ljspeech-vits-2023-11-29). diff --git a/egs/vctk/TTS/README.md b/egs/vctk/TTS/README.md new file mode 100644 index 0000000000..bb348e9a8f --- /dev/null +++ b/egs/vctk/TTS/README.md @@ -0,0 +1,14 @@ +# Introduction + +This CSTR VCTK Corpus includes speech data uttered by 110 English speakers with various accents. Each speaker reads out about 400 sentences, which were selected from a newspaper, the rainbow passage and an elicitation paragraph used for the speech accent archive. +The newspaper texts were taken from Herald Glasgow, with permission from Herald & Times Group. Each speaker has a different set of the newspaper texts selected based a greedy algorithm that increases the contextual and phonetic coverage. +The details of the text selection algorithms are described in the following paper: [C. Veaux, J. Yamagishi and S. King, "The voice bank corpus: Design, collection and data analysis of a large regional accent speech database,"](https://doi.org/10.1109/ICSDA.2013.6709856). + +The above information is from the [CSTR VCTK website](https://datashare.ed.ac.uk/handle/10283/3443). + +# VITS + +This recipe provides a VITS model trained on the VCTK dataset. + +Pretrained model can be found [here](https://huggingface.co/zrjin/icefall-tts-vctk-vits-2023-12-05), note that this model was pretrained on the Edinburgh DataShare VCTK dataset. +