Sundy1219/ctc_beam_search_lm
CTC+Beam_Search+kenlm 是用于以汉字为声学模型建模单元的解码系统
This tool helps convert spoken Chinese audio into written Chinese text, particularly for systems where the sound units correspond to individual Chinese characters. It takes the likelihoods (probabilities) of each character from an acoustic model and a list of possible characters, then outputs the most probable sequence of Chinese characters, effectively transcribing the speech.
No commits in the last 6 months.
Use this if you are building or working with a speech recognition system for Mandarin Chinese that uses Chinese characters as its basic acoustic modeling units and you need an efficient way to decode the audio into text.
Not ideal if your speech recognition system uses other languages, different acoustic modeling units (like phonemes), or if you only need a basic transcription without sophisticated language modeling.
Stars
48
Forks
24
Language
C++
License
—
Category
Last pushed
Jun 27, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/Sundy1219/ctc_beam_search_lm"
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)