facebookresearch/fairseq

Any plan to support TTS for cmn?

Open

#5,446 opened on Mar 1, 2024

View on GitHub
 (0 comments) (0 reactions) (0 assignees)Python (6,224 forks)batch import
enhancementhelp wantedneeds triage

Repository metrics

Stars
 (29,107 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

🚀 Feature Request

TTS support for cmn

Motivation

I'd like to try the TTS for cmn and compare it with NVIDIA Riva, Flytech, and Alibaba TTS etc.

Pitch

It seems that hak & nan have already been supported, it would be great if TTS for cmn can be supported ASAP :)

ISO 693-3 | Language Name | Language Family | Subgrouping | ASR | TTS | LID |   cmn | Chinese, Mandarin | Sino-Tibetan | Chinese | ✔️ (script: simplified) |   | ✔️ | Ethnologue hak | Chinese, Hakka | Sino-Tibetan | Chinese | ✔️ | ✔️ | ✔️ | Ethnologue nan | Chinese, Min Nan | Sino-Tibetan | Chinese | ✔️ | ✔️ | ✔️ | Ethnologue

Contributor guide

Research direction
Review existing TTS implementations for hak and nan in the Fairseq repository to understand the pattern for adding a new language code, then identify required data and training pipeline for Mandarin Chinese (cmn).
Tech stack
python
Domain
machine learningai
Issue type
Feature
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.
Over 1 week
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
Python
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
60