persephone-tools/persephone
A tool for automatic phoneme transcription
This tool automatically transcribes spoken audio into phonemes, even with very little existing transcribed speech data. You input audio files, and it outputs their phonemic transcriptions. It's designed for linguists and language documenters working with languages that have limited digital resources.
159 stars. No commits in the last 6 months.
Use this if you are a linguist or language documenter needing to create phonemic transcriptions for low-resource languages, especially when you only have a small amount of pre-transcribed audio.
Not ideal if you need orthographic (word-based) transcriptions, have access to large amounts of training data, or need an actively maintained project with a user-friendly graphical interface.
Stars
159
Forks
25
Language
Python
License
Apache-2.0
Category
Last pushed
Apr 18, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/persephone-tools/persephone"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
yeyupiaoling/MASR
Pytorch实现的流式与非流式的自动语音识别框架，同时兼容在线和离线识别，目前支持Conformer、Squeezeformer、DeepSpeech2模型，支持多种数据增强方法。
shivammehta25/Matcha-TTS
[ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching
coqui-ai/TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
DigitalPhonetics/IMS-Toucan
Controllable and fast Text-to-Speech for over 7000 languages!
gabrielmittag/NISQA
NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment