nttcslab-sp/torchain
WIP: pytorch FFI wrapper for Kaldi chain loss (a.k.a. Lattice Free MMI)
This project provides a critical component for developers building advanced speech recognition systems. It allows them to integrate Kaldi's Lattice-Free MMI (LF-MMI) loss function, which is highly effective for training acoustic models, directly into PyTorch-based deep learning workflows. By combining Kaldi's robust speech processing with PyTorch's flexibility, developers can create more accurate and efficient speech-to-text solutions.
No commits in the last 6 months.
Use this if you are a machine learning engineer or researcher developing custom automatic speech recognition (ASR) systems and need to leverage Kaldi's Chain loss within a PyTorch framework.
Not ideal if you are an end-user simply looking to transcribe audio or if you prefer off-the-shelf ASR solutions without deep customization.
Stars
20
Forks
5
Language
Python
License
—
Category
Last pushed
Feb 20, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/nttcslab-sp/torchain"
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