jfainberg/sincnet_adapt
Raw waveform adaptation with SincNet
This project helps improve the accuracy of automatic speech recognition (ASR) systems when encountering new speakers or different recording environments. It takes raw audio waveforms and an existing ASR model, then fine-tunes the model's acoustic parameters to better understand varied speech patterns. Speech researchers and developers working on ASR systems would use this to enhance their models' adaptability.
No commits in the last 6 months.
Use this if you need to adapt an existing automatic speech recognition (ASR) model to perform better on speech data from new speakers or acoustic conditions.
Not ideal if you are looking for an out-of-the-box, ready-to-deploy ASR system or a tool for general audio processing unrelated to speech recognition model adaptation.
Stars
12
Forks
—
Language
Python
License
—
Category
Last pushed
Mar 19, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/jfainberg/sincnet_adapt"
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