zzw922cn/Automatic_Speech_Recognition
End-to-end Automatic Speech Recognition for Madarian and English in Tensorflow
Implements multiple RNN architectures (BiRNN, DBiRNN, ResNet) with configurable cell types (LSTM, GRU) and includes DeepSpeech2 and Capsule Network models for character and phoneme-level recognition. Provides preprocessing pipelines for TIMIT, LibriSpeech, and WSJ datasets with Layer Normalization RNN variants for improved training efficiency, plus an integrated language modeling module for decoding.
2,839 stars. No commits in the last 6 months.
Stars
2,839
Forks
534
Language
Python
License
MIT
Category
Last pushed
Mar 24, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/zzw922cn/Automatic_Speech_Recognition"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
espnet/espnet
End-to-End Speech Processing Toolkit
yeyupiaoling/PPASR
基于PaddlePaddle实现端到端中文语音识别，从入门到实战，超简单的入门案例，超实用的企业项目。支持当前最流行的DeepSpeech2、Conformer、Squeezeformer模型
flashlight/wav2letter
Facebook AI Research's Automatic Speech Recognition Toolkit
yeyupiaoling/PaddlePaddle-DeepSpeech
基于PaddlePaddle实现的语音识别，中文语音识别。项目完善，识别效果好。支持Windows，Linux下训练和预测，支持Nvidia Jetson开发板预测。
philipperemy/deep-speaker
Deep Speaker: an End-to-End Neural Speaker Embedding System.