MingLunHan/CIF-PyTorch
[ICASSP 2020] CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition (A PyTorch implementation of Continuous Integrate-and-Fire mechanism).
This project helps speech recognition researchers and engineers convert raw audio recordings into text transcriptions more efficiently. It takes in speech audio data and outputs a sequence of text units, such as words or subwords. Researchers working on developing or improving automatic speech recognition (ASR) systems would use this to build faster and more accurate models.
No commits in the last 6 months.
Use this if you are developing an end-to-end speech recognition model and need to precisely control the alignment between speech input and text output without sacrificing speed.
Not ideal if you are looking for a ready-to-use, off-the-shelf speech-to-text application for general use, rather than a component for ASR model development.
Stars
79
Forks
6
Language
Python
License
Apache-2.0
Category
Last pushed
Jan 09, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/MingLunHan/CIF-PyTorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
TensorSpeech/TensorFlowASR
:zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2....
dangvansam/viet-asr
VietASR - Vietnamese Automatic Speech Recognition
wenet-e2e/wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit
xinjli/allosaurus
Allosaurus is a pretrained universal phone recognizer for more than 2000 languages
srvk/eesen
The official repository of the Eesen project