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).

35
/ 100
Emerging

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.

speech-to-text audio-transcription ASR-model-development natural-language-processing machine-learning-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

79

Forks

6

Language

Python

License

Apache-2.0

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.