csukuangfj / kaldi-native-fbank
Kaldi-compatible online fbank extractor without external dependencies
☆74Updated 2 months ago
Related projects: ⓘ
- Kaldi-compatible online & offline feature extraction with PyTorch, supporting CUDA, batch processing, chunk processing, and autograd - P…☆186Updated this week
- ☆34Updated 3 years ago
- ☆32Updated last month
- simple dnn based vad☆67Updated 5 years ago
- Python Wrapper of Silero VAD☆37Updated 2 months ago
- Went online decode demo☆30Updated 3 years ago
- 语音识别 论文 前沿☆42Updated 2 years ago
- ☆61Updated last year
- 3M: Multi-loss, Multi-path and Multi-level Neural Networks for speech recognition☆119Updated 2 years ago
- Memory efficient transducer loss computation☆68Updated 2 years ago
- A torch implementation of a recursion which turns out to be useful for RNN-T.☆138Updated last year
- An open-source implementation of sequence-to-sequence based speech processing engine☆38Updated last year
- One command to build TLG.fst for WeNet.☆27Updated last year
- ☆50Updated 3 years ago
- End-to-End Keyword Spotting (E2E-KWS) using a character level LSTM☆37Updated last year
- Some fast-ish algorithms for batch text search in moderate-sized collections, intended for data cleanup☆56Updated 3 weeks ago
- The project is associated with the recently-launched ICASSP 2022 Multi-channel Multi-party Meeting Transcription Challenge (M2MeT) to pro…☆111Updated 2 years ago
- A ctc decoder for both online and offline asr model☆57Updated 10 months ago
- MagicData-RAMC Dataset and Baseline☆49Updated 2 years ago
- Production first, nn-based on-device signal processing toolkit.☆63Updated last year
- Python wrapper for OpenFST and its extensions from Kaldi. Also support reading/writing ark/scp files☆47Updated 2 months ago
- This is the Python library for an unsupervised, fast method for robust voice activity detection (rVAD), as in the paper rVAD: An Unsuperv…☆126Updated 3 months ago
- ☆64Updated 2 years ago
- Computes the MWER (minimum WER) Loss with CTC beam search. Knowledge distillation for CTC loss.☆56Updated last year
- ☆31Updated last year
- A enterprise-grade Voice Activity Detector from modelscope and funasr.☆49Updated last year
- ☆75Updated 2 years ago
- Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context☆171Updated last week
- Colab notebooks for Next-gen Kaldi☆24Updated last month
- ☆30Updated 3 years ago