lectura-tts-multi
French text-to-speech pipeline (multi-speaker) — text to audio with speaker selection. Combines G2P pipeline with neural multi-speaker TTS (Conformer or FastPitch + HiFi-GAN).
Pipeline TTS multi-speaker du francais — texte vers audio avec choix de voix. Combine le pipeline G2P avec la synthese neuronale multi-speaker (Conformer ou FastPitch + HiFi-GAN).
Installation
pip install lectura-tts-multi # pipeline
pip install lectura-tts-multi[retimbre] # + conversion vocale zero-shot
Usage
from lectura_tts_multi import synthetiser
audio = synthetiser("Bonjour, comment allez-vous ?", speaker_id=0)
# audio : numpy array (int16, 22050 Hz)
Architecture
- G2P :
lectura-g2p— texte vers phonetique IPA - TTS :
lectura-multispeaker— phonetique vers audio multi-speaker (Conformer ou FastPitch, ONNX) - Retimbre (optionnel) :
lectura-vc-zeroshot— conversion vocale zero-shot
Licence
AGPL-3.0-or-later — voir LICENCE.txt. Modeles pre-entraines : voir MODEL_LICENCE.md.
Licence commerciale et modeles locaux disponibles — contacter admin@lectura.world.
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file lectura_tts_multi-1.0.1.tar.gz.
File metadata
- Download URL: lectura_tts_multi-1.0.1.tar.gz
- Upload date:
- Size: 2.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/6.2.0 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
b1193f8f5b24264b1382d1f8bb155a5dbb081560b95d1e45119e1dae9ba3ba95
|
|
| MD5 |
820fc4444a2e54cedc2c21be9a1aa61c
|
|
| BLAKE2b-256 |
99b53e3730b37cbb5c77c9eb5d7c210e208893acb7094965c68c3d669aa6d0cb
|
File details
Details for the file lectura_tts_multi-1.0.1-py3-none-any.whl.
File metadata
- Download URL: lectura_tts_multi-1.0.1-py3-none-any.whl
- Upload date:
- Size: 2.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/6.2.0 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
4f3b16c533a760f835b734a416d4948160c5b3a7193c999101b1e2949fb60ef0
|
|
| MD5 |
04c154d7a4f25c66122f886257151535
|
|
| BLAKE2b-256 |
5920fefd409ec9a0c2a98e6eeff866b95409e25bbdd21862ce5beee6192b555f
|