PaddlePaddle/PaddleSpeech

[TTS]英文数据 MFA 之前过滤标点，防止标点和单词黏连导致 OOV 变成 spn

Open

#2,443 opened on Sep 23, 2022

View on GitHub
 (2 comments) (0 reactions) (1 assignee)Python (9,453 stars) (1,702 forks)batch import
T2Sfeature requestgood first issue

Description

This issue does not include a description.

Contributor guide

Tech stack
python
Domain
backend
Issue type
bug
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
mostly clear
Prerequisites
PythonTTS frontend conceptsMFA
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
40
Research direction
Investigate the text frontend processing chain in PaddleSpeech, focusing on punctuation handling before MFA alignment. Look at files in `paddlespeech/t2s/frontend/` and the normalization pipeline. Identify where OOV tokens become 'spn' due to punctuation word concatenation and implement a filtering step to separate punctuation before MFA.