George0828Zhang/torch_cif
A fast parallel PyTorch implementation of the "CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition" https://arxiv.org/abs/1905.11235.
This tool helps researchers and machine learning engineers working on speech recognition systems. It takes raw speech features and their corresponding firing probabilities to produce integrated speech features, representing recognized speech units. Its primary users are those developing or experimenting with end-to-end speech recognition models.
No commits in the last 6 months. Available on PyPI.
Use this if you are implementing or researching speech recognition models and need a fast, parallel way to convert continuous speech features into discrete output units using the Continuous Integrate-and-Fire (CIF) mechanism.
Not ideal if you are a casual user looking for a ready-to-use speech-to-text application or do not have experience with PyTorch and deep learning.
Stars
36
Forks
4
Language
Python
License
MIT
Category
Last pushed
Feb 10, 2024
Commits (30d)
0
Dependencies
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/George0828Zhang/torch_cif"
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