Skip to content

Modèle Français 0.4

Pre-release
Pre-release
Compare
Choose a tag to compare
@lissyx lissyx released this 10 Mar 08:49
· 76 commits to master since this release
v0.6.0-fr-0.4
cec24e8
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.

Jeux de données :

  • Lingua Libre (~20h)
  • Common Voice FR (v2) (~290h, en autorisant jusqu'à 8 duplicatas)
  • Training Speech (~180h)
  • African Accented French (~15h)
  • M-AILABS French (~315h)

Total : ~820h

Paramètres :

  • LEARNING_RATE=0.0001
  • DROPOUT=0.3
  • BATCH_SIZE=64
  • LM_ALPHA=0.65
  • LM_BETA=1.45

Language Model : dump wikipedia + dump débats assemblée nationale.

Fonctionne avec DeepSpeech v0.6.1.

Résultats test set:

Test on /mnt/extracted/data/lingualibre/lingua_libre_Q21-fra-French_test.csv - WER: 0.541340, CER: 0.150946, loss: 5.962852
--------------------------------------------------------------------------------
WER: 5.000000, CER: 0.241379, loss: 3.496368
 - wav: file:///mnt/extracted/data/lingualibre/lingua_libre/Q21-fra-French/Lyokoï/électroencéphalographiquement.wav
 - src: "électroencéphalographiquement"
 - res: "électro en céphale orphique ment"
--------------------------------------------------------------------------------
WER: 4.000000, CER: 0.333333, loss: 3.654961
 - wav: file:///mnt/extracted/data/lingualibre/lingua_libre/Q21-fra-French/Lyokoï/aposématisme.wav
 - src: "aposématisme"
 - res: "a posé ma time"
--------------------------------------------------------------------------------
WER: 4.000000, CER: 0.400000, loss: 4.680493
 - wav: file:///mnt/extracted/data/lingualibre/lingua_libre/Q21-fra-French/WikiLucas00/oligoasthénotératospermie.wav
 - src: "oligoasthénotératospermie"
 - res: "aligoté notera to sperm"
--------------------------------------------------------------------------------
WER: 4.000000, CER: 0.285714, loss: 7.043005
 - wav: file:///mnt/extracted/data/lingualibre/lingua_libre/Q21-fra-French/WikiLucas00/octingentesimo.wav
 - src: "octingentesimo"
 - res: "acting en tesi mo"
--------------------------------------------------------------------------------
WER: 4.000000, CER: 0.500000, loss: 12.178319
 - wav: file:///mnt/extracted/data/lingualibre/lingua_libre/Q21-fra-French/Lyokoï/limousinerie.wav
 - src: "limousinerie"
 - res: "il vous i neri"
--------------------------------------------------------------------------------
WER: 4.000000, CER: 0.263158, loss: 17.644501
 - wav: file:///mnt/extracted/data/lingualibre/lingua_libre/Q21-fra-French/WikiLucas00/paléontologiquement.wav
 - src: "paléontologiquement"
 - res: "pale on a logiquement"
--------------------------------------------------------------------------------
WER: 4.000000, CER: 0.538462, loss: 20.121408
 - wav: file:///mnt/extracted/data/lingualibre/lingua_libre/Q21-fra-French/WikiLucas00/mielleusement.wav
 - src: "mielleusement"
 - res: "in a le cement"
--------------------------------------------------------------------------------
WER: 4.000000, CER: 0.454545, loss: 23.273678
 - wav: file:///mnt/extracted/data/lingualibre/lingua_libre/Q21-fra-French/Poslovitch/ennuagement.wav
 - src: "ennuagement"
 - res: "en eut age ment"
--------------------------------------------------------------------------------
WER: 4.000000, CER: 0.692308, loss: 36.408180
 - wav: file:///mnt/extracted/data/lingualibre/lingua_libre/Q21-fra-French/Xenophôn/Hondevilliers.wav
 - src: "hondevilliers"
 - res: "on ne vit le"
--------------------------------------------------------------------------------
WER: 4.000000, CER: 0.687500, loss: 38.046669
 - wav: file:///mnt/extracted/data/lingualibre/lingua_libre/Q21-fra-French/WikiLucas00/téléconsultation.wav
 - src: "téléconsultation"
 - res: "tel que les consultations"
--------------------------------------------------------------------------------
Test on /mnt/extracted/data/trainingspeech/ts_2019-04-11_fr_FR_test.csv - WER: 0.197745, CER: 0.059797, loss: 17.292450
--------------------------------------------------------------------------------
WER: 4.000000, CER: 1.333333, loss: 38.737186
 - wav: file:///mnt/extracted/data/trainingspeech/ts_2019-04-11_fr_FR/LeComteDeMonteCristoT1Chap5_0237.converted.wav
 - src: "espoir"
 - res: "n est ce soir"
--------------------------------------------------------------------------------
WER: 3.000000, CER: 1.000000, loss: 47.523190
 - wav: file:///mnt/extracted/data/trainingspeech/ts_2019-04-11_fr_FR/MonsieurLecoqP1C16_0188.converted.wav
 - src: "continuez"
 - res: "quand il est"
--------------------------------------------------------------------------------
WER: 2.000000, CER: 0.250000, loss: 0.010373
 - wav: file:///mnt/extracted/data/trainingspeech/ts_2019-04-11_fr_FR/MonsieurLecoqT2P16_0185.converted.wav
 - src: "chanlouineau"
 - res: "chan luneau"
--------------------------------------------------------------------------------
WER: 2.000000, CER: 0.142857, loss: 0.052286
 - wav: file:///mnt/extracted/data/trainingspeech/ts_2019-04-11_fr_FR/MonsieurLecoqP1C42_0070.converted.wav
 - src: "parbleu"
 - res: "par bleu"
--------------------------------------------------------------------------------
WER: 2.000000, CER: 0.142857, loss: 0.219133
 - wav: file:///mnt/extracted/data/trainingspeech/ts_2019-04-11_fr_FR/LeComteDeMonteCristoT1Chap3_0284.converted.wav
 - src: "pardieu"
 - res: "par dieu"
--------------------------------------------------------------------------------
WER: 2.000000, CER: 0.333333, loss: 1.239774
 - wav: file:///mnt/extracted/data/trainingspeech/ts_2019-04-11_fr_FR/LesMysteresDeParisT3P5C14_0002.converted.wav
 - src: "amitie"
 - res: "a miti"
--------------------------------------------------------------------------------
WER: 2.000000, CER: 0.384615, loss: 1.923999
 - wav: file:///mnt/extracted/data/trainingspeech/ts_2019-04-11_fr_FR/LeComteDeMonteCristoT1Chap24_0002.converted.wav
 - src: "eblouissement"
 - res: "et boisement"
--------------------------------------------------------------------------------
WER: 2.000000, CER: 0.250000, loss: 2.610425
 - wav: file:///mnt/extracted/data/trainingspeech/ts_2019-04-11_fr_FR/MonsieurLecoqT2P33_0032.converted.wav
 - src: "chimeres"
 - res: "chi mere"
--------------------------------------------------------------------------------
WER: 2.000000, CER: 0.500000, loss: 3.350882
 - wav: file:///mnt/extracted/data/trainingspeech/ts_2019-04-11_fr_FR/MonsieurLecoqT2P04_0012.converted.wav
 - src: "hola"
 - res: "a la"
--------------------------------------------------------------------------------
WER: 2.000000, CER: 0.400000, loss: 7.205533
 - wav: file:///mnt/extracted/data/trainingspeech/ts_2019-04-11_fr_FR/LeDernierJourDunCondamne_0712.converted.wav
 - src: "lirlonfa malure"
 - res: "le lan fan maure"
--------------------------------------------------------------------------------
Test on /mnt/extracted/data/M-AILABS/fr_FR/fr_FR_test.csv - WER: 0.090398, CER: 0.025351, loss: 11.177062
--------------------------------------------------------------------------------
WER: 2.000000, CER: 0.166667, loss: 3.342017
 - wav: file:///mnt/extracted/data/M-AILABS/fr_FR/female/ezwa/monsieur_lecoq/wavs/monsieur_lecoq_2_36_f000179.wav
 - src: "dubois"
 - res: "du bois"
--------------------------------------------------------------------------------
WER: 2.000000, CER: 0.857143, loss: 8.253085
 - wav: file:///mnt/extracted/data/M-AILABS/fr_FR/female/nadine_eckert_boulet/les_tribulations_dun_chinoise/wavs/les_tribulations_dun_chinoise_10_f000043.wav
 - src: "bidulph"
 - res: "le bip"
--------------------------------------------------------------------------------
WER: 2.000000, CER: 0.375000, loss: 10.294103
 - wav: file:///mnt/extracted/data/M-AILABS/fr_FR/male/gilles_g_le_blanc/lupin_contre_holmes/wavs/lupin_contre_holmes_13_f000184.wav
 - src: "personne"
 - res: "le songe"
--------------------------------------------------------------------------------
WER: 2.000000, CER: 6.000000, loss: 20.541677
 - wav: file:///mnt/extracted/data/M-AILABS/fr_FR/female/nadine_eckert_boulet/les_mysteres_de_paris/wavs/les_mysteres_de_paris_4_13_f000027.wav
 - src: "m"
 - res: "on ne "
--------------------------------------------------------------------------------
WER: 1.500000, CER: 0.400000, loss: 4.110573
 - wav: file:///mnt/extracted/data/M-AILABS/fr_FR/male/gilles_g_le_blanc/lupin_contre_holmes/wavs/lupin_contre_holmes_07_f000165.wav
 - src: "m destange"
 - res: "mais des tange"
--------------------------------------------------------------------------------
WER: 1.500000, CER: 0.266667, loss: 4.140529
 - wav: file:///mnt/extracted/data/M-AILABS/fr_FR/male/gilles_g_le_blanc/lupin_contre_holmes/wavs/lupin_contre_holmes_14_f000218.wav
 - src: "langlais ricana"
 - res: "l'anglais et cana"
--------------------------------------------------------------------------------
WER: 1.200000, CER: 0.279070, loss: 58.677330
 - wav: file:///mnt/extracted/data/M-AILABS/fr_FR/female/ezwa/monsieur_lecoq/wavs/monsieur_lecoq_2_40_f000027.wav
 - src: "incompréhensible balbutia t il inimaginable"
 - res: "un coupé aussi ble balbutiant il imaginable"
--------------------------------------------------------------------------------
WER: 1.000000, CER: 0.125000, loss: 0.046964
 - wav: file:///mnt/extracted/data/M-AILABS/fr_FR/male/gilles_g_le_blanc/lupin_contre_holmes/wavs/lupin_contre_holmes_11_f000012.wav
 - src: "ganimard"
 - res: "gaimard"
--------------------------------------------------------------------------------
WER: 1.000000, CER: 0.142857, loss: 0.094500
 - wav: file:///mnt/extracted/data/M-AILABS/fr_FR/male/gilles_g_le_blanc/lupin_contre_holmes/wavs/lupin_contre_holmes_01_f000115.wav
 - src: "gerbois"
 - res: "gerboise"
--------------------------------------------------------------------------------
WER: 1.000000, CER: 0.150000, loss: 0.097039
 - wav: file:///mnt/extracted/data/M-AILABS/fr_FR/female/ezwa/monsieur_lecoq/wavs/monsieur_lecoq_2_49_f000013.wav
 - src: "chanlouineau fusillé"
 - res: "chanoine au fusillé"
--------------------------------------------------------------------------------
Test on /mnt/extracted/data/African_Accented_French/African_Accented_French/African_Accented_French_test.csv - WER: 0.436413, CER: 0.241087, loss: 41.901531
--------------------------------------------------------------------------------
WER: 2.000000, CER: 0.777778, loss: 38.173145
 - wav: file:///mnt/extracted/data/African_Accented_French/African_Accented_French/speech/devtest/ca16/007/afc-gabon_16.06.11_007_read_0080.wav
 - src: "canadiens"
 - res: "dans la"
--------------------------------------------------------------------------------
WER: 2.000000, CER: 1.268293, loss: 265.257477
 - wav: file:///mnt/extracted/data/African_Accented_French/African_Accented_French/speech/train/yaounde/answers/ctell4-58/ctell4-58-168.wav
 - src: "combien de temps avez vous cessé de fumer"
 - res: "c'est un petit ma voie chez ce que de l'age de fumée pour la vie ou donner"
--------------------------------------------------------------------------------
WER: 1.750000, CER: 2.172414, loss: 420.618073
 - wav: file:///mnt/extracted/data/African_Accented_French/African_Accented_French/speech/train/yaounde/answers/ctell2-24/ctell2-24-146.wav
 - src: "quand est ce qu' on l' a volé"
 - res: "c'est impossible de savoir quand reste on l'a voulue parce que ce n'est pas l'objet volé"
--------------------------------------------------------------------------------
WER: 1.500000, CER: 0.700000, loss: 28.472775
 - wav: file:///mnt/extracted/data/African_Accented_French/African_Accented_French/speech/train/yaounde/answers/ctell4-57/ctell4-57-131.wav
 - src: "bonne nuit"
 - res: "bon ni messe"
--------------------------------------------------------------------------------
WER: 1.500000, CER: 1.100000, loss: 163.632797
 - wav: file:///mnt/extracted/data/African_Accented_French/African_Accented_French/speech/train/yaounde/answers/ctell3-51/ctell3-51-084.wav
 - src: "de quelle couleur est sa barbe"
 - res: "il n'y a pas de barre mais si l'on avait "
--------------------------------------------------------------------------------
WER: 1.333333, CER: 1.000000, loss: 65.997902
 - wav: file:///mnt/extracted/data/African_Accented_French/African_Accented_French/speech/train/yaounde/answers/ctell3-45/ctell3-45-238.wav
 - src: "êtes vous blessé"
 - res: "ce que monsieur de "
--------------------------------------------------------------------------------
WER: 1.250000, CER: 1.066667, loss: 64.391045
 - wav: file:///mnt/extracted/data/African_Accented_French/African_Accented_French/speech/train/yaounde/answers/ctell4-55/ctell4-55-093.wav
 - src: "que mesure t il"
 - res: "en mars un maître sur "
--------------------------------------------------------------------------------
WER: 1.250000, CER: 1.285714, loss: 128.277420
 - wav: file:///mnt/extracted/data/African_Accented_French/African_Accented_French/speech/train/yaounde/answers/ctell5-78/ctell5-78-253.wav
 - src: "où fait il mal"
 - res: "au niveau de la vendra"
--------------------------------------------------------------------------------
WER: 1.250000, CER: 1.000000, loss: 144.560806
 - wav: file:///mnt/extracted/data/African_Accented_French/African_Accented_French/speech/train/yaounde/answers/ctell3-39/ctell3-39-099.wav
 - src: "quelle est sa religion"
 - res: "je crois qu'il est protestant"
--------------------------------------------------------------------------------
WER: 1.250000, CER: 0.782609, loss: 239.664795
 - wav: file:///mnt/extracted/data/African_Accented_French/African_Accented_French/speech/train/yaounde/answers/ctell2-20/ctell2-20-046.wav
 - src: "pendant combien de temps croyez vous rester là"
 - res: "selon comment le porte et mélangés et que je pourrai"
--------------------------------------------------------------------------------
Test on /mnt/extracted/data/cv-fr/clips/test.csv - WER: 0.322719, CER: 0.154181, loss: 43.217838
--------------------------------------------------------------------------------
WER: 2.333333, CER: 1.352941, loss: 97.013374
 - wav: file:///mnt/extracted/data/cv-fr/clips/common_voice_fr_18910747.wav
 - src: "un futur lointain"
 - res: "ce qui affecte le tatara qui se"
--------------------------------------------------------------------------------
WER: 2.000000, CER: 0.333333, loss: 12.225451
 - wav: file:///mnt/extracted/data/cv-fr/clips/common_voice_fr_17766587.wav
 - src: "bienvenue"
 - res: "bien menu"
--------------------------------------------------------------------------------
WER: 2.000000, CER: 0.700000, loss: 18.917130
 - wav: file:///mnt/extracted/data/cv-fr/clips/common_voice_fr_17485009.wav
 - src: "scandaleux"
 - res: "star de"
--------------------------------------------------------------------------------
WER: 2.000000, CER: 0.857143, loss: 23.581638
 - wav: file:///mnt/extracted/data/cv-fr/clips/common_voice_fr_17353440.wav
 - src: "anglais"
 - res: "en gré"
--------------------------------------------------------------------------------
WER: 2.000000, CER: 0.437500, loss: 30.835510
 - wav: file:///mnt/extracted/data/cv-fr/clips/common_voice_fr_19625291.wav
 - src: "aquiles sierra almagrera espagne"
 - res: "à qui les sera allemand era et pan"
--------------------------------------------------------------------------------
WER: 1.750000, CER: 0.740741, loss: 77.242172
 - wav: file:///mnt/extracted/data/cv-fr/clips/common_voice_fr_19599883.wav
 - src: "semaine d etudes liturgique"
 - res: "le seul ban de étude de qui"
--------------------------------------------------------------------------------
WER: 1.666667, CER: 0.823529, loss: 94.504822
 - wav: file:///mnt/extracted/data/cv-fr/clips/common_voice_fr_17430039.wav
 - src: "à la bibliothèque"
 - res: "elle a lu de tec"
--------------------------------------------------------------------------------
WER: 1.500000, CER: 0.250000, loss: 6.661707
 - wav: file:///mnt/extracted/data/cv-fr/clips/common_voice_fr_17383853.wav
 - src: "où c'est"
 - res: "ou c est"
--------------------------------------------------------------------------------
WER: 1.500000, CER: 0.900000, loss: 26.406160
 - wav: file:///mnt/extracted/data/cv-fr/clips/common_voice_fr_18787090.wav
 - src: "ayez pitié"
 - res: "il est utile"
--------------------------------------------------------------------------------
WER: 1.500000, CER: 0.437500, loss: 29.822001
 - wav: file:///mnt/extracted/data/cv-fr/clips/common_voice_fr_19047565.wav
 - src: "digital networks"
 - res: "di vita nepos"
--------------------------------------------------------------------------------
Assets 5
Loading