Luka0612 / asr_transformerLinks
采用transformer end2end训练语音识别ASR
☆0Updated 5 years ago
Alternatives and similar repositories for asr_transformer
Users that are interested in asr_transformer are comparing it to the libraries listed below
Sorting:
- Tensorflow version of DFSMN☆49Updated 7 years ago
- MXNet implementation of RNN Transducer (Graves 2012): Sequence Transduction with Recurrent Neural Networks☆139Updated 4 years ago
- ☆106Updated 4 years ago
- Seq2Seq Speech Recognition with Transformer on Mandarin Chinese☆116Updated 5 years ago
- 采用端到端方法构建声学模型,以字为建模单元,采用DCNN-CTC网络结构。☆70Updated 6 years ago
- ☆143Updated 4 years ago
- Implementations for FSMN (Feedforward Sequential Memory Network), cFSMN, DFSMN, and PFSMN units☆9Updated 6 years ago
- A Pytorch Implementation of Transducer Model for End-to-End Speech Recognition☆236Updated 5 years ago
- A pytorch_lightning reimplementation of the Transducer module from ESPnet.☆77Updated 4 years ago
- An LDA/PLDA estimator using KALDI in python for speaker verification tasks☆100Updated 8 years ago
- Chinese keyword spotting model using LSTM RNN☆173Updated 6 years ago
- ☆55Updated 5 years ago
- Implements of CTC, Speech-Transformer and CIF for end-to-end speech recognition with pytorch☆22Updated 4 years ago
- A PyTorch implementation of Listen, Attend and Spell (LAS), an End-to-End ASR framework.☆200Updated 6 years ago
- 基于卷积神经网络的语音识别声学模型的研究☆175Updated 5 years ago
- A pytorch based end2end speech recognition system.☆115Updated 4 years ago
- A No-Recurrence Sequence-to-Sequence Model for Speech Recognition☆376Updated 2 years ago
- CTC end -to-end ASR for timit and 863 corpus.☆218Updated 5 years ago
- 基于dVector的说话人识别keras☆90Updated 4 years ago
- 调用百度语音识别API,Python SDK。并评估WER词错误率。☆9Updated 6 years ago
- E2E system with LF-MMI; word N-gram for Mandarin☆165Updated 3 years ago
- transformer for ASR-systerm (via tensorflow2.0)☆114Updated 6 years ago
- ASR for Chinese Mandarin☆75Updated 7 years ago
- 方言分类,pytorch☆43Updated 6 years ago
- python codes to extract MFCC and FBANK speech features for Kaldi☆66Updated 6 years ago
- Computes the MWER (minimum WER) Loss with CTC beam search. Knowledge distillation for CTC loss.☆58Updated last year
- Listen, Attend and Spell - PyTorch Implementation☆17Updated 6 years ago
- mWER loss implementation in tensorflow☆31Updated 4 years ago
- End-to-end trained speech recognition system, based on RNNs and the connectionist temporal classification (CTC) cost function.☆122Updated 5 years ago
- Implementation of the work presented in "CNN based Query by Example Spoken Term Detection"☆32Updated 6 years ago