tramphero / kaldi
This is now the official location of the Kaldi project.
☆722Updated 5 years ago
Related projects ⓘ
Alternatives and complementary repositories for kaldi
- Alibaba speech technology☆913Updated 6 years ago
- 集成Webrtc的VAD,用于切分音频文件☆340Updated 4 years ago
- 中文语音识别☆803Updated 6 years ago
- speech recognition based on tensorflow 1.0.0☆139Updated 7 years ago
- An Automatic Speech Recognition Frame ,一个中文语音识别的完整框架, 提供了多个模型☆246Updated 3 years ago
- 语音识别理论、论文和PPT☆586Updated 3 months ago
- 一个执着于让CPU\端侧-Model逼近GPU-Model性能的项目,CPU上的实时率(RTF)小于0.1☆461Updated last month
- 【中文语音 识别 】【验证码识别】☆118Updated last year
- Mandarin ASR system based on tensorflow☆108Updated 6 years ago
- 中文语音识别; Mandarin Automatic Speech Recognition;☆1,879Updated 3 months ago
- ESIM for Multi-turn Response Selection Task☆582Updated 5 years ago
- Connectionist Temporal Classification (CTC) Automatic Speech Recognition☆297Updated 6 years ago
- ☆327Updated 5 years ago
- unit-uskit☆251Updated 3 years ago
- A TensorFlow implementation of Google's Tacotron speech synthesis with pre-trained model☆282Updated 5 years ago
- A Demo of Mandarin/Chinese TTS frontend☆277Updated 2 years ago
- Turn Chinese natural language into structured data 中文自然语言理解☆1,512Updated 3 months ago
- Chinese Text-to-Speech web service☆306Updated 3 years ago
- 专门面向中文用户的机器学习相关的学习资料大集合☆149Updated 3 years ago
- 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。☆682Updated this week
- DELTA is a deep learning based natural language and speech processing platform.☆1,591Updated 7 months ago
- Google Summer of Code 2018 Project: Automatic Speech Recognition for Speech-to-Text on Chinese☆115Updated 6 years ago
- (已过时)中文语音合成,改自 https://github.com/Rayhane-mamah/Tacotron-2 和 https://github.com/begeekmyfriend/Tacotron-2☆299Updated 2 years ago
- Deepmind's Tacotron-2 Tensorflow implementation☆162Updated 4 years ago
- FAQ-based Question Answering System☆2,585Updated 3 years ago
- A toolkit to implement segmentation on speech based on BIC and nerual network, such as BiLSTM☆122Updated 5 years ago
- an open-source implementation of sequence-to-sequence based speech processing engine☆952Updated last year
- Chinese Speech To Text Using Wavenet☆159Updated last year