whull / end2end_ASRLinks
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 4 years ago
Alternatives and similar repositories for end2end_ASR
Users that are interested in end2end_ASR are comparing it to the libraries listed below
Sorting:
- Went online decode demo☆31Updated 4 years ago
- kaldi cnn-tdnnf baseline☆13Updated 4 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 4 years ago
- 基于随机森林和条件随机场的中文韵律预测模型☆28Updated last year
- ☆40Updated 4 years ago
- 以音素建模构建NN-CTC声学模型☆15Updated 6 years ago
- CTC decoder with hotwords for ASR.☆27Updated 6 months ago
- ☆13Updated 4 years ago
- ☆33Updated 4 years ago
- An upgrade framework for train and validate compare with icefall using Lightning.☆13Updated 6 months ago
- ☆33Updated 3 years ago
- Detect emotion from audio☆13Updated 6 years ago
- ☆11Updated last year
- it's a train acoustics model code lib☆27Updated 5 years ago
- repository for paper "Audio-Visual Speech Recognition in MISP2021 Challenge: Dataset Release and Deep Analysis"☆17Updated 3 years ago
- ☆12Updated 3 years ago
- ☆11Updated 2 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 5 years ago
- ☆22Updated 6 years ago
- One command to start a streaming ASR server.☆12Updated last year
- Speech command recognition with capsule network & various NNs / KWS on Google Speech Command Dataset.☆25Updated 6 years ago
- Keyword Search Recipe for Subword ASR☆30Updated 6 years ago
- ☆15Updated last year
- it's ASR decoder and make graph project☆33Updated 3 years ago
- A ctc decoder for both online and offline asr model☆64Updated last year
- 本项目使用中文人声的数据集,在Speech Denoising with Deep Feature Losses网络的基础上fine-tune,得到对中文音频有更好去噪效果的结果☆28Updated 5 years ago
- 机器学习资源☆16Updated 5 years ago
- ☆61Updated 2 years ago
- tacotron-2(pytorch) + melgan(pytorch) chinese TTS☆26Updated 2 years ago
- Arxiv automatically obtains the latest article service.☆11Updated 5 years ago