oleges1/quartznet-pytorch
Quartznet implementation on pytorch [https://arxiv.org/abs/1910.10261]
This project helps convert spoken audio into written text, a process known as Automatic Speech Recognition (ASR). It takes audio recordings from common datasets like CommonVoice, Librispeech, or LJSpeech, and outputs their transcriptions. It's designed for researchers or developers working on building and evaluating speech-to-text systems.
No commits in the last 6 months.
Use this if you need to quickly implement and experiment with a high-performance speech-to-text model (QuartzNet) using common datasets.
Not ideal if you are looking for an off-the-shelf, ready-to-use application without any development or model training.
Stars
26
Forks
7
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Jul 16, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/oleges1/quartznet-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