whull / end2end_ASR
端到端语音识别实现;包含LAS、CTC、RNNT解码方式,模型SA(MHA)、LSTM、CNN、DFSMN等
☆15Updated 3 years ago
Alternatives and similar repositories for end2end_ASR:
Users that are interested in end2end_ASR are comparing it to the libraries listed below
- 基于单语种语料的中英混合语音识别算法-同花顺算法挑战赛-2021年9-10月双月赛☆14Updated 3 years ago
- 以音素建模构建NN-CTC声学模型☆15Updated 5 years ago
- ☆37Updated 3 years ago
- Went online decode demo☆29Updated 3 years ago
- ☆31Updated 3 years ago
- 将normalize过的中文文本,做逆向normalize。具体功能即实现 chinese_text_normalization的逆向版本。☆13Updated 3 years ago
- SChunk-Encoder (Transformer or Conformer) for streaming E2E ASR☆9Updated 2 years ago
- tacotron-2(pytorch) + melgan(pytorch) chinese TTS☆26Updated last year
- kaldi cnn-tdnnf baseline☆13Updated 3 years ago
- Feedforward Sequential Memory Networks☆15Updated 2 years ago
- 基于Kaldi的小词汇量汉语语音识别,使用DNN训练☆27Updated 6 years ago
- A ctc decoder for both online and offline asr model☆63Updated last year
- 基于随机森林和条件随机场的中文韵律预测模型☆28Updated 8 months ago
- Utilizes ONNX Runtime for audio denoising.☆42Updated this week
- ☆13Updated 4 years ago
- 分享在深蓝学院《语音识别:从入门到精通》第一期课程学习过程中完成的课后作业,供参考。☆21Updated 4 years ago
- An Automatic Speech Recognition using GMM & HMM.☆19Updated 5 years ago
- repository for paper "Audio-Visual Speech Recognition in MISP2021 Challenge: Dataset Release and Deep Analysis"☆16Updated 2 years ago
- 深蓝学院语音课程《语音识别从入门到精通》课程作业☆22Updated 5 years ago
- Listen, Attend and Spell - PyTorch Implementation☆17Updated 6 years ago
- We design a spectral compression mapping (SCM) for full-band speech enhancement, and propose a two-stage stream named MHA-DPCRN☆24Updated 2 years ago
- A library for adding punctuation into a text from ASR.☆17Updated last year
- Addressing Text-dependent Speaker Verification Using Singing Speech☆9Updated 5 years ago
- 语音增强TFCN论文复现☆40Updated 3 years ago
- Code for paper "Dual-Path Style Learning for End-to-End Noise-Robust Speech Recognition"☆41Updated last year
- One command to start a streaming ASR server.☆11Updated 6 months ago
- Implementaion RNN tranceducer☆22Updated 5 years ago
- One command to build TLG.fst for WeNet.☆30Updated 2 years ago
- End-to-End Keyword Spotting (E2E-KWS) using a character level LSTM☆39Updated 2 years ago
- E2E ASR system☆14Updated 2 years ago