LJ Speech English TTS

This upload contains a TTS model which was trained on the LJ Speech dataset using these transcriptions but with explicit phoneme duration markers removed. The model is trained using tacotron-cli.

The model achieves the following values on the validation set:

• MOS naturalness: 3.49 ± 0.28 (GT: 4.17 ± 0.23)
• MOS intelligibility: 4.44 ± 0.21 (GT: 4.63 ± 0.19)
• mean mel-cepstral distance: 30.96
• mean penalty: 0.1341

Files:

• 101000.pt
  • checkpoint after 500 epochs with a batch size of 64
• 1-setup-env.sh
  • script to install all required tools
• 2-create-dataset.sh
  • script to create the base dataset using public resources
• 3-create-train-val-set.sh
  • script to create the training set and validation set
• 4-start-training.sh
  • script to start training using Tacotron
• 5-convert-english-to-ipa.sh
  • script to prepare English texts for synthesis by transcribing them to IPA
• 6-synthesize.sh
  • script to synthesize IPA transcribed text
• example-north-wind.zip
  • contains an example passage which was synthesized using the model

The model is able to synthesize the following symbols:

• vowels: i, u, æ, ɑ, ɔ, ə, ɛ, ɪ, ʊ, ʌ
• diphthongs: aɪ, aʊ, eɪ, oʊ, ɔɪ
• r-colored vowels: ɔr, ər, ɛr, ɪr, ʊr, ʌr
• consonants: b, d, dʒ, f, h, j, k, l, m, n, p, r, s, t, tʃ, v, w, z, ð, ŋ, ɡ, ʃ, θ
• breaks: SIL0, SIL1, SIL2, SIL3
• special characters: . ? ! , : ; - — " ' ( ) [ ]

Each vowel, diphthong and r-colored vowel can have a leading stress symbol ˈˌ attached, e.g., ˈoʊ.

Example:

The North Wind and the Sun were disputing which was the stronger, when a traveler came along wrapped in a warm cloak.

ð|ə|SIL0|n|ˈɔr|θ|SIL0|w|ˈɪ|n|d|SIL0|ə|n|d|SIL0|ð|ə|SIL0|s|ˈʌ|n|SIL0|w|ˈʌr|SIL0|d|ɪ|s|p|j|ˈu|t|ɪ|ŋ|SIL0|w|ˈɪ|tʃ|SIL0|w|ˈɑ|z|SIL0|ð|ə|SIL0|s|t|r|ˈɔ|ŋ|ər|,|SIL1|w|ˈɛ|n|SIL0|ə|SIL0|t|r|ˈæ|v|ə|l|ər|SIL0|k|ˈeɪ|m|SIL0|ə|l|ˈɔ|ŋ|SIL0|r|ˈæ|p|t|SIL0|ɪ|n|SIL0|ə|SIL0|w|ˈɔr|m|SIL0|k|l|ˈoʊ|k|.|SIL2