R1ckShi/SeACo-Paraformer
[ICASSP2023] Source code, model links and open test sets for paper SeACo-Paraformer.
This project offers an improved way to convert spoken Mandarin into text, especially when specific words or phrases (hotwords) need to be accurately recognized. You provide audio recordings and a list of important hotwords, and it outputs the transcribed text with enhanced accuracy for those key terms. This is for developers building sophisticated speech-to-text applications where precise recognition of product names, technical jargon, or custom vocabulary is critical.
No commits in the last 6 months.
Use this if you are a speech technology developer needing to build an Automatic Speech Recognition (ASR) system that effectively recognizes and prioritizes specific 'hotwords' in spoken Chinese.
Not ideal if you are looking for a ready-to-use end-user application for general transcription without customization needs.
Stars
44
Forks
1
Language
—
License
—
Category
Last pushed
Mar 15, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/R1ckShi/SeACo-Paraformer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
Uberi/speech_recognition
Speech recognition module for Python, supporting several engines and APIs, online and offline.
cmusphinx/pocketsphinx
A small speech recognizer
tensorflow/lingvo
Lingvo
modelscope/FunASR
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models,...
PyThaiNLP/pythaiasr
Python Thai Automatic Speech Recognition