Mildemelwe/Non-English-Tacotron-2-Training-Notebook
Tacotron 2 training notebook supporting Japanese, French, and Mandarin
This tool helps you create custom text-to-speech voices for non-English languages like Japanese, French, and Mandarin. You provide recordings of someone speaking and their corresponding transcriptions, and the tool outputs a trained voice model. This is for voice artists, content creators, educators, or anyone needing to generate speech in specific non-English voices for applications like audiobooks, language learning tools, or virtual assistants.
No commits in the last 6 months.
Use this if you need to train a unique, synthetic voice from your own audio recordings for Japanese, French, or Mandarin text-to-speech applications.
Not ideal if you need a quick, off-the-shelf voice without custom training, or if your primary language is English or not one of the currently supported non-English languages.
Stars
11
Forks
2
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Nov 19, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/Mildemelwe/Non-English-Tacotron-2-Training-Notebook"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
bshall/Tacotron
A PyTorch implementation of Location-Relative Attention Mechanisms For Robust Long-Form Speech Synthesis
Kyubyong/dc_tts
A TensorFlow Implementation of DC-TTS: yet another text-to-speech model
DemisEom/SpecAugment
A Implementation of SpecAugment with Tensorflow & Pytorch, introduced by Google Brain
Rayhane-mamah/Tacotron-2
DeepMind's Tacotron-2 Tensorflow implementation
Kyubyong/tacotron
A TensorFlow Implementation of Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model