IDER CLINIC AUDIO RESOURCE CREDITS
Updated 20 September 2026

The clinic lessons, worked cases, explanations and assessments are IDER in-house training materials. The audio resources below support their English and French delivery. Resource contributors and original readers are not represented as IDER employees or as endorsing these lessons.

ENGLISH AUDIO RESOURCES

Cori, medium-quality English voice resource.
Resource compiled and trained by Bryce Beattie from LibriVox recordings, identified as public domain in its model card.
Model card: https://huggingface.co/rhasspy/piper-voices/blob/main/en/en_GB/cori/medium/MODEL_CARD
Contributor: https://brycebeattie.com/files/tts/
Recording source: https://librivox.org/

LibriTTS, high-quality English voice resource, distributed through the Rhasspy/Piper voice collection by Michael Hansen.
Source corpus: Heiga Zen, Viet Dang, Rob Clark, Yu Zhang, Ron J. Weiss, Ye Jia, Zhifeng Chen and Yonghui Wu (2019), LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech.
Corpus: https://www.openslr.org/60/
Paper: https://arxiv.org/abs/1904.02882
Model card: https://huggingface.co/rhasspy/piper-voices/blob/main/en/en_US/libritts/high/MODEL_CARD
Licence: Creative Commons Attribution 4.0 International, https://creativecommons.org/licenses/by/4.0/
The model card records training from scratch on the train-clean-360 corpus.
The selected resource speaker index is 2, mapped to corpus speaker 4535.

LibriTTS is derived from LibriSpeech and the LibriVox recordings. LibriSpeech: Vassil Panayotov, Guoguo Chen, Daniel Povey and Sanjeev Khudanpur (2015), LibriSpeech: An ASR Corpus Based on Public Domain Audio Books.
Source: https://www.openslr.org/12/
Licence: Creative Commons Attribution 4.0 International, https://creativecommons.org/licenses/by/4.0/

FRENCH AUDIO RESOURCES

Multilingual LibriSpeech (MLS), medium-quality French voice resource, distributed through the Rhasspy/Piper voice collection by Michael Hansen.
Source corpus: Vineel Pratap, Qiantong Xu, Anuroop Sriram, Gabriel Synnaeve and Ronan Collobert (2020), MLS: A Large-Scale Multilingual Dataset for Speech Research.
Corpus: https://www.openslr.org/94/
Paper: https://arxiv.org/abs/2012.03411
Model card: https://huggingface.co/rhasspy/piper-voices/blob/main/fr/fr_FR/mls/medium/MODEL_CARD
Licence: Creative Commons Attribution 4.0 International, https://creativecommons.org/licenses/by/4.0/
The model card records training from scratch. The selected resource speaker indices are 0 and 1, mapped to corpus speakers 1840 and 3698.

PRODUCTION

Audio is produced locally using Piper 1.8.0. Speech timing, pauses and volume are adjusted for the lessons, and the resulting audio is encoded for web playback. The lesson text is original IDER training material; it is not the text of the source audiobooks.
Piper software: https://github.com/OHF-Voice/piper1-gpl
Piper software licence: GNU General Public License, version 3 or later, https://www.gnu.org/licenses/gpl-3.0.html

The source-resource licences apply to the identified resources. They do not imply endorsement of IDER, and they are not a grant of rights in unrelated IDER materials.