robmsmt/KerasDeepSpeech
A Keras CTC implementation of Baidu's DeepSpeech for model experimentation
Implements multiple DeepSpeech architectures (DS1 with bidirectional LSTM, DS2 with 1D convolutions and GRU) alongside custom model variants, all trained with CTC loss for end-to-end speech recognition. Includes live audio recording and testing capabilities plus utilities for building custom voice datasets, enabling rapid prototyping without external annotation. Integrates with external language models and supports deployment via Core ML for iOS/Android platforms.
243 stars. No commits in the last 6 months.
Stars
243
Forks
76
Language
Python
License
AGPL-3.0
Category
Last pushed
Mar 17, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/robmsmt/KerasDeepSpeech"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
githubharald/CTCWordBeamSearch
Connectionist Temporal Classification (CTC) decoder with dictionary and language model.
githubharald/CTCDecoder
Connectionist Temporal Classification (CTC) decoding algorithms: best path, beam search, lexicon...
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)