smeetrs/deep_avsr
A PyTorch implementation of the Deep Audio-Visual Speech Recognition paper.
This project offers a speech-to-text transcription solution that can process audio, video (lip movements), or a combination of both. It takes speech recordings as input and outputs the spoken words as text, even in noisy environments where audio alone might be unclear. This is ideal for researchers and engineers working on automated transcription or assistive technologies for speech.
243 stars. No commits in the last 6 months.
Use this if you need to transcribe spoken language from video footage or audio recordings, especially when dealing with poor audio quality or silent lip-read scenarios.
Not ideal if you need a simple, out-of-the-box transcription service without delving into model training or setup, as this requires some technical configuration.
Stars
243
Forks
42
Language
Python
License
MIT
Category
Last pushed
Feb 15, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/smeetrs/deep_avsr"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
githubharald/CTCDecoder
Connectionist Temporal Classification (CTC) decoding algorithms: best path, beam search, lexicon...
githubharald/CTCWordBeamSearch
Connectionist Temporal Classification (CTC) decoder with dictionary and language model.
nl8590687/ASRT_SpeechRecognition
A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统
athena-team/athena
an open-source implementation of sequence-to-sequence based speech processing engine
hirofumi0810/tensorflow_end2end_speech_recognition
End-to-End speech recognition implementation base on TensorFlow (CTC, Attention, and MTL training)