pandeydivesh15/AVSR-Deep-Speech
Google Summer of Code 2017 Project: Development of Speech Recognition Module for Red Hen Lab
This project offers a speech-to-text module designed for researchers working with news videos or other media containing both audio and visual information. It takes raw video or audio files along with their time-aligned transcripts as input. The output is a highly accurate text transcription, making it ideal for media analysts, archivists, or social scientists studying broadcast content.
No commits in the last 6 months.
Use this if you need to transcribe speech from videos, especially when visual cues (like lip movements) are present and can improve accuracy over audio-only methods.
Not ideal if you have short audio files with existing transcripts and do not need to leverage visual information for transcription.
Stars
45
Forks
19
Language
Python
License
GPL-2.0
Category
Last pushed
Aug 29, 2017
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/pandeydivesh15/AVSR-Deep-Speech"
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)