Ressources for End-to-End French Text-to-Speech

Here are 205013 utts from 1406 chapters of Librivox/Litteratureaudio, read by 106 different speakers (54 females & 52 males): speakers: ['NEB', 'DG', 'RO', 'IZ', 'AD', 'MLB', 'YB', 'AA', 'TH', 'JLF', 'PL', 'PB', 'EZWA', 'XELLE', 'BERNARD', 'REMI', 'PAULINE', 'CD', 'OCEANE', 'TLT', 'HELENE', 'GAELLE', 'CYPRIEN', 'LAURIPSUM', 'KINFO', 'KARINE', 'JANICO', 'DD', 'GH', 'ALAIN', 'TRISTISEULT', 'JULIE', 'LYRA', 'BRUANT', 'MYRNELEON', 'DMC', 'ORANGENO', 'REDBIRD', 'RAMINA', 'SOPHIE', 'ELISE', 'MONIQUE', 'ALEXANDRE', 'LOSTANIA', 'EMERAUDE', 'EUCALYPTUS', 'TSEMERIS', 'ROMY', 'EOLE', 'JULIEN', 'BIDOU', 'HKN', 'AYAK', 'ZENOBIE', 'EXMACHINA', 'FRANCOISE', 'ZECKOU', 'KITOUNE', 'CLAUDE', 'ALDOR', 'LAURETTE', 'AMY', 'LOCTURNE', 'DAGOBERT', 'KAMISOLE', 'CAROLINE', 'NATHALIE', 'STEPHANIE', 'THOMAS', 'JBAILLY', 'NAF', 'GIOVANNI', 'EMY', 'PEJUGA', 'GRAIGOLIN', 'CEBES', 'MARLENE', 'FAO', 'MARTINE', 'GERARDF', 'SIXB', 'STEPHANE', 'DAVID', 'ANDRED', 'LAURENCE', 'JCGUAN', 'HARPO', 'ALAINC', 'BIGMALL', 'QUENTINF', 'CHRISTIANATTARD', 'JONATHAN', 'IAMNOT', 'JPB', 'THEOTEX', 'MARIECA', 'MILADY', 'PHILIPPESEIGNEUR', 'PLUME', 'PASCALF', 'YSABELLA', 'MORGANE', 'THIERRY', 'RITOU', 'BARYTONX', 'CLEMENTINE'] females: ['NEB', 'RO', 'IZ', 'AD', 'MLB', 'AA', 'PL', 'EZWA', 'XELLE', 'PAULINE', 'OCEANE', 'HELENE', 'GAELLE', 'LAURIPSUM', 'KARINE', 'TRISTISEULT', 'JULIE', 'LYRA', 'MYRNELEON', 'ORANGENO', 'RAMINA', 'SOPHIE', 'ELISE', 'MONIQUE', 'EMERAUDE', 'EUCALYPTUS', 'ROMY', 'EOLE', 'ZENOBIE', 'EXMACHINA', 'FRANCOISE', 'KITOUNE','CLAUDE', 'LAURETTE', 'AMY', 'LOCTURNE', 'CAROLINE', 'STEPHANIE', 'NATHALIE', 'JBAILLY', 'NAF', 'MARTINE', 'MARLENE', 'EMY', 'LAURENCE', 'SIXB', 'JCGUAN', 'MARIECA', 'MILADY', 'PLUME', 'YSABELLA', 'MORGANE', 'RITOU', 'CLEMENTINE'}; Text and alignements have been hand_checked. The total duration is 177:12:22.080. Each .wav file (sampled at 22050Hz) corresponds to one entire chapter. The format of the filenames is:{author's acronym}_{book's acronym}_{reader's acronym}_{volume's number}_{chapter's number} The files wav_22050_NEB.tar , wav_22050_AD.tar , wav_22050_DG.tar, wav_22050_RO.tar, wav_22050_IZ.tar, wav_22050_MLB.tar and wav_22050_others.tar respectively contain the .wav files for speakers NEB, AD, DG, RO, IZ, MLB and the other 104 speakers. Corresponding HD Videos (.mov) are available for speaker AD in mp4_AD_Reading.tar , mp4_AD_Expressive1.tar and mp4_AD_Expressive2.tar. The ALL.csv file gives text or phonetic alignments for utterances in 4 fields separated by '|':{filename}|{start_ms}|{end_ms}|{text or phonetic content}. Most utterances are separated by at least a pause of 400ms. The intervals [start_ms:end_ms] comprise leading and trailing silences of 130ms (since wavs are entire chapters, these silences are "true" ambient silences). When phonetic alignment has been performed and hand-checked, 2 additional fields have been added: {aligned phones}|{durations in ms}. Each input character or phone has a corresponding aligned phone and a duration. Note that all aligned utterances start and end with an aligned phone of 130ms. The set of aligned phones comprises: The set of input phones The silence: '__' The symbol '_' for silent characters, e.g. "chat" is aligned with 's^ _ a _' 29 combined aligned phones ('a&i', 'a&j', 'b&q', 'd&q','d&z', 'd&z^', 'f&q', 'g&q', 'g&z', 'j&i', 'j&u', 'j&q', 'i&j', 'k&q', 'k&s', 'k&s&q', 'l&q', 'm&q', 'n&q', 'r&w', 'r&q', 's&q', 't&q', 't&s', 't&s^', 'w&a', 'z&q', 'p&q') that align to only one character, e.g. "expatrier" is aligned with 'e^ k&s p a t r i&j e _' Text is in UTF8. '«»','¬', '~','""','()','[]' are respectively used for speaking quotes, turn switches, three dots, quoted expression, aside quotes, notes. Because of rare occurrences, 'ö' has been transcribed as 'oe'. Paragraphs (two consecutive carriage returns in the original text) are cued by a special character '§'. It usually ends an utterance but could be used within an utterance if its associated pause is too short. Leading and trailing silences are aligned with silences and punctuations & quotes when available. When no leading quotes are available, the utterance is prefixed with the character associated with the trailing character of the previous utterance if belonging to the same text otherwise with "§" (indicating the beginning of a new chapter). Words or group of words spoken with emphasis are surrounded by the special character: "#" e.g. "Elle #haussa# les épaules." When available, phonetic content is given per word in curly brackets '{}'. We use 39 phonetic symbols: oral vowels: a (fa), e (fée), e^ (fait), x (feu), x^ (coeur), i (riz), y (fut), u (fou), o (faux), o^ (porc) schwa: q (gage) nasal vowels: a~ (rang), e~ (fin), x~ (un), o~ (rond) semi-vowels: h (huit), w (ouate), j (hier) consonants: p (pas), t (tas), k (cas), b (bas), d (dos), g (gars), f (faux), s (sot) , s^ (chat), v (vu), z (zut), z^ (jus), r (riz), l (la), m (ma), n (non), n~ (oignon), ng (camping)