zw76859420/ASR_WORD
采用端到端方法构建声学模型，以字为建模单元，采用DCNN-CTC网络结构。
This project helps speech recognition engineers build and improve acoustic models, specifically those that process speech into individual Chinese characters. It takes recorded Chinese speech audio as input and outputs the recognized text in character form. Speech recognition researchers and developers, particularly those working on end-to-end models with character-level units, would use this.
No commits in the last 6 months.
Use this if you are a speech recognition researcher or developer looking for an existing end-to-end acoustic model, built with DCNN-CTC, that uses Chinese characters as its basic modeling unit.
Not ideal if you need a highly accurate, production-ready speech-to-text system, as this is a foundational model with a high character error rate intended for further development.
Stars
70
Forks
20
Language
Python
License
AGPL-3.0
Category
Last pushed
Jan 26, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/zw76859420/ASR_WORD"
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)