MorrisXu-Driving/Improving_DeepSpeech_2_by_RNN_Transducer_Pytorch_Implementation
In this repository, based on Deep Speech 2, two losses, CTC and RNN-T are compared.
This project helps machine learning engineers and researchers improve Automatic Speech Recognition (ASR) model performance. It compares the DeepSpeech 2 model with an enhanced version using an RNN-Transducer, taking audio features as input and outputting transcribed text. This is for those working on building or optimizing speech-to-text systems.
No commits in the last 6 months.
Use this if you are a machine learning engineer or researcher specifically working on optimizing DeepSpeech 2 for better word error rates in speech recognition tasks.
Not ideal if you are a non-technical end-user looking for a ready-to-use speech-to-text application, as this project focuses on model comparison and improvement for developers.
Stars
8
Forks
1
Language
Python
License
—
Category
Last pushed
May 24, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/MorrisXu-Driving/Improving_DeepSpeech_2_by_RNN_Transducer_Pytorch_Implementation"
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