lectura-decodeur — Decodeur phonetique CTC du francais
Transcription audio vers phonemes IPA via un modele CNN-BiGRU-CTC medium (10.6M params, PER ~4.34%).
Le modele medium supporte les sigles, formules (nombres, dates, calculs) et la parole courante grace a un vocabulaire etendu de 59 tokens et un fine-tuning specialise.
Installation
# Avec backend ONNX (recommande)
pip install lectura-decodeur[onnx]
# Sans ONNX (mode API uniquement)
pip install lectura-decodeur
Utilisation
import numpy as np
from lectura_decodeur import creer_engine
engine = creer_engine()
# Audio PCM float32 mono 16kHz
audio = np.zeros(16000, dtype=np.float32) # 1 seconde de silence
result = engine.transcrire(audio)
print(result) # chaine IPA : "b ɔ̃ ʒ u ʁ | l ə | m ɔ̃ d"
Modele
| Caracteristique | Valeur |
|---|---|
| Architecture | CNN [48, 96] + BiGRU 384x4 + CTC head |
| Parametres | 10.6M |
| Performance | PER ~4.34% (formules v2) |
| Vocabulaire | 59 tokens (46 phones IPA + liaisons + ponctuation + speciaux) |
| Entrainement | Pre-train corpus complet + fine-tune formules/sigles multispeaker |
Backends
| Backend | Dependance | Latence | Modele |
|---|---|---|---|
| ONNX Runtime | onnxruntime |
~10 ms/s audio | phone_ctc_int8.onnx (38 Mo) |
| API | aucune | ~100 ms/s audio | serveur Lectura |
Parametres audio
- Sample rate : 16 kHz
- Format : PCM float32 mono
- Mel : 80 bins, n_fft=512, hop=160, win=400
Licence
Double licence : AGPL-3.0 (libre) + Licence Commerciale (payante).
Les modeles ONNX sont distribues separement — voir MODEL_LICENCE.md.
Auteur
Max Carriere — lectura.world
1 maintainer
Metadata
1 maintainer
Release files for lectura-decodeur 3.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| lectura_decodeur-3.1.0.tar.gz | 31.7 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| lectura_decodeur-3.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 63.6 kB
Release files / lectura_decodeur-3.1.0.tar.gz
| Download URL | lectura_decodeur-3.1.0.tar.gz |
|---|---|
| Size | 31.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
94da970a849456453411b95aa2262bed978d68ee8dd2e2d7bf5add6222679705
|
|
BLAKE2b-256 checksum How to use checksums |
1c0c75084cc238151a9ac7ff5b84fedb59f53872723b6ce38116b0c3b8f8c222
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.9
|
Release files / lectura_decodeur-3.1.0-py3-none-any.whl
| Download URL | lectura_decodeur-3.1.0-py3-none-any.whl |
|---|---|
| Size | 32.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
0e3641c66429e031794ac2a1d5c12ab54c28d7d2197d44aa88b015f5bc3a2998
|
|
BLAKE2b-256 checksum How to use checksums |
84197024427d3bc020ff4a05125300918d760209e215835b4d65fdec19a9c14b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.9
|
